OpenAI · launched 29 Sept 2026
GPT-6.1 Sol
An upgrade to GPT-6 Sol for coding, professional work and computer use, with cached input priced 50% lower.
Read the official announcementEarlier release. View its successor, GPT-6.2 Sol, for the latest launch results. This model's details and pricing remain available below.
- Vendor
- OpenAI
- Launch date
- 29 Sept 2026
- Input price
- $2.00 / 1M tokens
- Output price
- $10 / 1M tokens
- Cached input
- $0.10 / 1M tokens
- Batch discount
- 50%
- Context window
- 1.05M tokens
- Max output
- 128K tokens
- Input types
- Text, Image, File
- API model ID
- gpt-6.1-sol
- OpenRouter ID
- openai/gpt-6.1-sol
Listed rates apply up to 272K input tokens. Above 272K, input costs $4, cached input $0.20 and output $15 per million tokens for the full request.
Input price
$2.00
was $2.00 · Same price
Output price
$10
was $10 · Same price
Blended price
$4.00
was $4.00 · Same price
Listed rates apply up to 272K input tokens. Above 272K, input costs $4, cached input $0.20 and output $15 per million tokens for the full request.
- DeepSWE v1.1high effort · $0.65 per task · reported by OpenAI75.22%
- GDP.pdfhigh effort · $0.35 per task · reported by OpenAI32%
- AutomationBench 1.0.6max effort · $0.30 per task · reported by OpenAI36.1%
- OSWorld 2.0 (offline set)max effort · $1.27 per task · reported by OpenAI71.42%
- Terminal-Bench Science 0.1max effort · $5.47 per task · reported by OpenAI57.02%
- Factual error rate on difficult prompts(lower is better)xhigh effort · $0.10 per task · reported by OpenAI4.12%
- Agents' Last Exam v1.1max effort · $2.02 per task · reported by OpenAI72.45%
- Terminal-Bench Science 0.1max effort · $5.47 per task · reported by OpenAI57%
- Vals Science Index v1max effort · $1.36 per task · reported by OpenAI59.6%
- FrontierCode 2.0max effort · $1.03 per task · reported by OpenAI39%
- LifeValmax effort · $1.27 per task · reported by OpenAI79.5%
- Harvey-LAB-AA v1.1max effort · $2.48 per task · reported by OpenAI6.9%
- BenchCAD 2.1 Coremax effort · $1.61 per task · reported by OpenAI52.6%
- AutomationBench 1.0.6max effort · $0.30 per task · reported by OpenAI36.1%
- SecureSWEmax effort · $0.87 per task · reported by OpenAI49.7%
- PatchBenchmax effort · $0.74 per task · reported by OpenAI71%
- Agents' Last Exam v1max effort · $2.00 per task · reported by OpenAI58.6%
- MMMU-Pro (Vision)max effort · $0.013 per task · reported by OpenAI86.3%
- OSWorld 2.1 (offline set)max effort · $1.15 per task · reported by OpenAI78%
- Factual error rate on difficult prompts(lower is better)max effort · $0.12 per task · reported by OpenAI4.4%
- Terminal-Bench 4.0max effort · $1.98 per task · reported by OpenAI55.9%
- Terminal-Bench Science 0.1max effort · $5.47 per task · reported by OpenAI57%
Price compared with other models
| Model | Launched | Input / 1M | Output / 1M | Cached / 1M | Blended / 1M | vs GPT-6.1 Sol |
|---|---|---|---|---|---|---|
| Claude Haiku 5.5AnthropicListed prices and comparisons apply to prompts up to 100K tokens. Above 100K, input costs $0.50, output $2.50 and cache reads $0.05 per million tokens. | 7 Oct 2026 | $0.10 | $0.50 | $0.01 | $0.20 | 95% cheaper |
| GPT-6 LunaOpenAI | 22 Sept 2026 | $0.10 | $0.50 | $0.01 | $0.20 | 95% cheaper |
| GPT-5.6 LunaOpenAI | 9 Jul 2026 | $0.20 | $1.20 | $0.02 | $0.45 | 89% cheaper |
| Gemini 3.5 Flash-LiteGoogle DeepMindText, image, video and audio inputs share the listed rate. Cache storage and grounding are billed separately. | 21 Jul 2026 | $0.30 | $2.50 | $0.03 | $0.85 | 79% cheaper |
| Gemini 3.8 FlashGoogle DeepMindIntroductory rates through 31 December 2026. From 1 January 2027, input is $1.50, output $7.50 and cached input $0.15 per million tokens. Cache storage and grounding are billed separately. | 2 Sept 2026 | $0.75 | $3.75 | $0.075 | $1.50 | 63% cheaper |
| Claude Haiku 4.5Anthropic | 15 Oct 2025 | $1.00 | $5.00 | $0.10 | $2.00 | 50% cheaper |
| GPT-6.1 TerraOpenAIListed rates apply up to 272K input tokens. Above 272K, input costs $2, cached input $0.10 and output $7.50 per million tokens for the full request. | 26 Oct 2026 | $1.00 | $5.00 | $0.05 | $2.00 | 50% cheaper |
| Grok 4.7SpaceXAIBase rates apply up to 200K context tokens; higher-context requests use different rates. Batch API is not supported. The separate fast variant costs twice as much. | 21 Sept 2026 | $2.00 | $6.00 | $0.50 | $3.00 | 25% cheaper |
| Claude Sonnet 5Anthropic | 30 Jun 2026 | $2.00 | $10 | $0.20 | $4.00 | Same price |
| Claude Sonnet 5.5AnthropicCache reads were reduced from $0.20 to $0.10 per million tokens on 7 October 2026. | 28 Sept 2026 | $2.00 | $10 | $0.10 | $4.00 | Same price |
| Gemini 4 ArgonGoogle DeepMindIntroductory rates through 30 November 2026. From 1 December 2026, input is $4, output $20 and cached input $0.20 per million tokens. Caching is implicit only. Long decode raises the output limit to 1,048,576 tokens. | 30 Sept 2026 | $2.00 | $10 | $0.10 | $4.00 | Same price |
| GPT-6 SolOpenAI · previous generationListed rates apply up to 272K input tokens. Above 272K, input costs $4, cached input $0.40 and output $15 per million tokens for the full request. | 22 Sept 2026 | $2.00 | $10 | $0.20 | $4.00 | Same price |
| GPT-6.1 SolOpenAIListed rates apply up to 272K input tokens. Above 272K, input costs $4, cached input $0.20 and output $15 per million tokens for the full request. | 29 Sept 2026 | $2.00 | $10 | $0.10 | $4.00 | Baseline |
| GPT-6.2 SolOpenAIListed rates apply up to 272K input tokens. Above 272K, input costs $4, cached input $0.20 and output $15 per million tokens for the full request. | 17 Nov 2026 | $2.00 | $10 | $0.10 | $4.00 | Same price |
| Gemini 3.1 ProGoogle DeepMind · PreviewRates apply to prompts up to 200K tokens. Above 200K, input is $4, output $18 and cached input $0.40 per million tokens. Cache storage and grounding are billed separately. | 19 Feb 2026 | $2.00 | $12 | $0.20 | $4.50 | 13% more |
| GPT-5.6 TerraOpenAIOpenAI's model documentation supports the Batch API but does not list a batch price. | 9 Jul 2026 | $2.00 | $12 | $0.20 | $4.50 | 13% more |
| Claude Opus 5.5Anthropic | 22 Sept 2026 | $4.00 | $20 | $0.20 | $8.00 | 2× the price |
| GPT-5.6 SolOpenAIPrice before the GPT-6 launch, from OpenAI's announcement. OpenRouter now lists $2 / $10. | 9 Jul 2026 | $4.00 | $20 | – | $8.00 | 2× the price |
| Claude Opus 5Anthropic | 24 Jul 2026 | $5.00 | $25 | $0.50 | $10 | 2.5× the price |
| Claude Fable 5.2Anthropic | 9 Nov 2026 | $8.00 | $40 | $0.20 | $16 | 4× the price |
| GPT-6.2 AstraOpenAIListed rates apply up to 272K input tokens. Above 272K, input costs $16, cached input $0.80 and output $60 per million tokens for the full request. | 17 Nov 2026 | $8.00 | $40 | $0.40 | $16 | 4× the price |
| Claude Fable 5Anthropic | 9 Jun 2026 | $10 | $50 | $1.00 | $20 | 5× the price |
| Claude Fable 5.1Anthropic | 1 Sept 2026 | $10 | $50 | $0.25 | $20 | 5× the price |
| GPT-6 AstraOpenAI | 4 Sept 2026 | $10 | $50 | $1.00 | $20 | 5× the price |
GPT-6.1 Sol and GPT-6 Sol rates were checked on 8 October 2026 against OpenAI model documentation. USD per million tokens, checked 2 Oct 2026 via OpenRouter. Comparison uses the blended price (3 input tokens for every output token). Haiku 5.5 and Sonnet 5.5 prices were updated from Anthropic's 7 October 2026 announcement. Gemini and Grok prices were rechecked against official Google and xAI documentation on 27 October 2026. GPT-6.1 Terra prices were checked against OpenAI documentation on 27 October 2026. Claude Fable 5.2 prices are from Anthropic's 9 November 2026 announcement.
Official benchmark results
Reported by OpenAI on 29 Sept 2026 · exact values
| Benchmark | GPT-6.1 Sol | GPT-6 Sol | GPT-6 Astra | GPT-6 Luna |
|---|---|---|---|---|
| Failure to disclose a broken search toolSafety evaluation · Max effort | 2.1% | 4.92% | 1.5% | 28.67% |
| Reviewer bypass attemptsSafety evaluation · Max effort | 0% | 0% | 0% | 0.26% |
| Warning circumventionSafety evaluation · Max effort | 23.48% | 64.39% | 17.42% | 42.37% |
| Computer-use safety stress testSafety evaluation · Xhigh effort | 4.32% | 17.39% | 2.4% | 13.7% |
- Bold marks the best reported score in each row.
- All rates are lower-is-better. These targeted evaluations stress challenging scenarios and do not represent typical usage.
- Exact values from the embedded announcement chart data. No cost values were published for these evaluations.
Score against cost · reported by OpenAI on 29 Sept 2026 · exact values
Agentic software engineering performance across reasoning effort settings.
- GPT-6.1 Sol
- GPT-6 Sol
- GPT-6 Astra
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Sol | low | 64.38% | $0.17 |
| GPT-6.1 Sol | medium | 73.01% | $0.42 |
| GPT-6.1 Sol | high | 75.22% | $0.65 |
| GPT-6.1 Sol | xhigh | 71.9% | $0.79 |
| GPT-6.1 Sol | max | 71.9% | $1.57 |
| GPT-6 Sol | low | 37.17% | $0.16 |
| GPT-6 Sol | medium | 56.64% | $0.38 |
| GPT-6 Sol | high | 65.27% | $0.64 |
| GPT-6 Sol | xhigh | 66.59% | $1.00 |
| GPT-6 Sol | max | 68.81% | $2.74 |
| GPT-6 Astra | low | 67.04% | $1.60 |
| GPT-6 Astra | medium | 72.79% | $3.08 |
| GPT-6 Astra | high | 73.23% | $3.92 |
| GPT-6 Astra | xhigh | 74.12% | $4.43 |
| GPT-6 Astra | max | 73.23% | $7.50 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Score against cost · reported by OpenAI on 29 Sept 2026 · exact values
Accuracy on professional questions using complex PDF documents.
- GPT-6.1 Sol
- GPT-6 Sol
- GPT-6 Astra
- Claude Opus 5.5 with fallbacks
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Sol | low | 27% | $0.33 |
| GPT-6.1 Sol | medium | 30% | $0.34 |
| GPT-6.1 Sol | high | 32% | $0.35 |
| GPT-6.1 Sol | xhigh | 31.8% | $0.37 |
| GPT-6.1 Sol | max | 31% | $0.42 |
| GPT-6 Sol | low | 21.8% | $0.33 |
| GPT-6 Sol | medium | 25.4% | $0.34 |
| GPT-6 Sol | high | 28% | $0.35 |
| GPT-6 Sol | xhigh | 23.8% | $0.37 |
| GPT-6 Sol | max | 24.8% | $0.43 |
| GPT-6 Astra | low | 30.4% | $1.70 |
| GPT-6 Astra | medium | 30.4% | $1.72 |
| GPT-6 Astra | high | 31% | $1.79 |
| GPT-6 Astra | xhigh | 32.2% | $1.91 |
| GPT-6 Astra | max | 31% | $2.08 |
| Claude Opus 5.5 with fallbacks | low | 25.6% | $0.76 |
| Claude Opus 5.5 with fallbacks | medium | 25.6% | $0.80 |
| Claude Opus 5.5 with fallbacks | high | 28.8% | $0.83 |
| Claude Opus 5.5 with fallbacks | xhigh | 26.6% | $0.96 |
| Claude Opus 5.5 with fallbacks | max | 26.2% | $1.55 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- Opus 5.5 results use fallback models as reported by OpenAI; these are not standalone Opus 5.5 results.
Score against cost · reported by OpenAI on 29 Sept 2026 · exact values
End-to-end business workflows using 47 tools across sales, marketing, operations, support, finance and HR.
- GPT-6.1 Sol
- GPT-6 Sol
- GPT-6 Astra
- Claude Opus 5.5 with fallbacks
- Claude Fable 5.1 with Opus 5 fallback
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Sol | low | 24.7% | $0.16 |
| GPT-6.1 Sol | medium | 31.7% | $0.19 |
| GPT-6.1 Sol | high | 33.2% | $0.23 |
| GPT-6.1 Sol | xhigh | 35.5% | $0.25 |
| GPT-6.1 Sol | max | 36.1% | $0.30 |
| GPT-6 Sol | low | 21.16% | $0.19 |
| GPT-6 Sol | medium | 26.94% | $0.21 |
| GPT-6 Sol | high | 31.2% | $0.24 |
| GPT-6 Sol | xhigh | 33.18% | $0.27 |
| GPT-6 Sol | max | 31.96% | $0.34 |
| GPT-6 Astra | low | 30.3% | $1.08 |
| GPT-6 Astra | medium | 34.1% | $1.27 |
| GPT-6 Astra | high | 37.1% | $1.44 |
| GPT-6 Astra | xhigh | 39% | $1.50 |
| GPT-6 Astra | max | 41.4% | $1.73 |
| Claude Opus 5.5 with fallbacks | low | 24.2% | $0.51 |
| Claude Opus 5.5 with fallbacks | medium | 29.53% | $0.65 |
| Claude Opus 5.5 with fallbacks | high | 33.03% | $0.71 |
| Claude Opus 5.5 with fallbacks | xhigh | 35.77% | $0.89 |
| Claude Opus 5.5 with fallbacks | max | 42.47% | $1.44 |
| Claude Fable 5.1 with Opus 5 fallback | max | 31.4% | $2.45 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- Opus 5.5 results use fallback models as reported by OpenAI; these are not standalone Opus 5.5 results.
- Fable 5.1 is reported at max effort only. Its cost omits fallbacks, which occurred on approximately 40% of tasks, so its actual cost is higher.
Score against cost · reported by OpenAI on 29 Sept 2026 · exact values
Partial reward on long-horizon computer-use workflows, using the offline set from release v2026.08.08.
- GPT-6.1 Sol
- GPT-6 Sol
- GPT-6 Astra
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Sol | low | 58.96% | $0.42 |
| GPT-6.1 Sol | medium | 66.84% | $0.77 |
| GPT-6.1 Sol | high | 69.56% | $0.96 |
| GPT-6.1 Sol | xhigh | 69.38% | $1.05 |
| GPT-6.1 Sol | max | 71.42% | $1.27 |
| GPT-6 Sol | low | 43.9% | $1.01 |
| GPT-6 Sol | medium | 54% | $1.38 |
| GPT-6 Sol | high | 58.29% | $1.71 |
| GPT-6 Sol | xhigh | 60.54% | $2.30 |
| GPT-6 Sol | max | 64.43% | $3.37 |
| GPT-6 Astra | low | 62.17% | $2.72 |
| GPT-6 Astra | medium | 69.25% | $5.36 |
| GPT-6 Astra | high | 70.02% | $6.91 |
| GPT-6 Astra | xhigh | 71.27% | $7.49 |
| GPT-6 Astra | max | 73.49% | $9.44 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Score against cost · reported by OpenAI on 29 Sept 2026 · exact values
Scientific research tasks completed through a terminal.
- GPT-6.1 Sol
- GPT-6 Sol
- GPT-6 Astra
- Claude Opus 5.5 with fallbacks
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Sol | low | 43.71% | $1.79 |
| GPT-6.1 Sol | medium | 47.56% | $2.34 |
| GPT-6.1 Sol | high | 51.14% | $2.76 |
| GPT-6.1 Sol | xhigh | 53.71% | $2.89 |
| GPT-6.1 Sol | max | 57.02% | $5.47 |
| GPT-6 Sol | low | 9.17% | $3.00 |
| GPT-6 Sol | medium | 14.49% | $4.41 |
| GPT-6 Sol | high | 14.61% | $4.63 |
| GPT-6 Sol | xhigh | 25.29% | $6.77 |
| GPT-6 Sol | max | 27.59% | $12.2 |
| GPT-6 Astra | low | 55.43% | $11.4 |
| GPT-6 Astra | medium | 57.43% | $12.3 |
| GPT-6 Astra | high | 62% | $15 |
| GPT-6 Astra | xhigh | 60.86% | $15.8 |
| GPT-6 Astra | max | 68.1% | $23.8 |
| Claude Opus 5.5 with fallbacks | max | 63.33% | $23.2 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- Opus 5.5 results use fallback models as reported by OpenAI; these are not standalone Opus 5.5 results.
Error rate against cost · reported by OpenAI on 29 Sept 2026 · exact values
Answers containing at least one factual error on deliberately difficult prompts. Lower is better.
- GPT-6.1 Sol
- GPT-6 Sol
- GPT-6 Astra
Show data table
| Model | Effort | Answers with any factual error (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Sol | low | 7.72% | $0.045 |
| GPT-6.1 Sol | medium | 6.29% | $0.056 |
| GPT-6.1 Sol | high | 4.52% | $0.082 |
| GPT-6.1 Sol | xhigh | 4.12% | $0.10 |
| GPT-6.1 Sol | max | 4.61% | $0.13 |
| GPT-6 Sol | low | 11.42% | $0.05 |
| GPT-6 Sol | medium | 6.86% | $0.069 |
| GPT-6 Sol | high | 5.14% | $0.099 |
| GPT-6 Sol | xhigh | 4.52% | $0.13 |
| GPT-6 Sol | max | 4.57% | $0.18 |
| GPT-6 Astra | low | 6.26% | $0.24 |
| GPT-6 Astra | medium | 4.41% | $0.31 |
| GPT-6 Astra | high | 3.9% | $0.48 |
| GPT-6 Astra | xhigh | 3.99% | $0.60 |
| GPT-6 Astra | max | 3.91% | $0.79 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- Prompts are de-identified conversations where users flagged an earlier model error. They are not representative of typical usage.
Score against cost · reported by OpenAI on 17 Nov 2026 · exact values
Long-horizon professional workflows completed by agents.
- GPT-6.2 Astra
- GPT-6.2 Sol
- GPT-6 Astra
- GPT-6.1 Sol
- Claude Fable 5.2
- Claude Opus 5.5
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.2 Astra | low | 65.77% | $0.47 |
| GPT-6.2 Astra | medium | 72.06% | $1.06 |
| GPT-6.2 Astra | high | 75.96% | $2.05 |
| GPT-6.2 Astra | xhigh | 78.33% | $2.89 |
| GPT-6.2 Astra | max | 77.61% | $4.47 |
| GPT-6.2 Sol | low | 66.65% | $0.27 |
| GPT-6.2 Sol | medium | 70.26% | $0.57 |
| GPT-6.2 Sol | high | 72.04% | $0.69 |
| GPT-6.2 Sol | xhigh | 72.48% | $0.86 |
| GPT-6.2 Sol | max | 73.04% | $1.32 |
| GPT-6 Astra | low | 67.87% | $5.40 |
| GPT-6 Astra | medium | 71.16% | $6.21 |
| GPT-6 Astra | high | 71.04% | $6.87 |
| GPT-6 Astra | xhigh | 71.68% | $7.56 |
| GPT-6 Astra | max | 73.14% | $8.99 |
| GPT-6.1 Sol | low | 60.98% | $0.21 |
| GPT-6.1 Sol | medium | 68.77% | $0.46 |
| GPT-6.1 Sol | high | 72.34% | $0.98 |
| GPT-6.1 Sol | xhigh | 71.92% | $0.98 |
| GPT-6.1 Sol | max | 72.45% | $2.02 |
| Claude Fable 5.2 | max | 72.79% | $60.1 |
| Claude Opus 5.5 | max | 71.6% | $17.6 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- Claude Fable 5.2 leaderboard results exclude nine tasks that used a fallback model, as reported by OpenAI.
- OpenAI's chart also shows Gemini 4 Carbon, which is not in the tracker, so its results are left out.
Score against cost · reported by OpenAI on 17 Nov 2026 · exact values
Scientific research workflows carried out in a terminal.
- GPT-6.2 Astra
- GPT-6.2 Sol
- GPT-6 Astra
- GPT-6.1 Sol
- Claude Fable 5.2 (mini-swe-agent harness)
- Claude Opus 5.5
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.2 Astra | low | 56.3% | $2.50 |
| GPT-6.2 Astra | medium | 72.3% | $4.20 |
| GPT-6.2 Astra | high | 74.9% | $5.20 |
| GPT-6.2 Astra | xhigh | 74% | $5.37 |
| GPT-6.2 Astra | max | 77.1% | $7.15 |
| GPT-6.2 Sol | low | 43.4% | $0.86 |
| GPT-6.2 Sol | medium | 63.1% | $1.34 |
| GPT-6.2 Sol | high | 67.7% | $1.51 |
| GPT-6.2 Sol | xhigh | 64.3% | $1.61 |
| GPT-6.2 Sol | max | 68% | $2.21 |
| GPT-6 Astra | low | 55.4% | $11.4 |
| GPT-6 Astra | medium | 57.4% | $12.3 |
| GPT-6 Astra | high | 62% | $14.9 |
| GPT-6 Astra | xhigh | 60.9% | $15.8 |
| GPT-6 Astra | max | 68.1% | $23.8 |
| GPT-6.1 Sol | low | 43.7% | $1.79 |
| GPT-6.1 Sol | medium | 47.6% | $2.34 |
| GPT-6.1 Sol | high | 51.1% | $2.76 |
| GPT-6.1 Sol | xhigh | 53.7% | $2.89 |
| GPT-6.1 Sol | max | 57% | $5.47 |
| Claude Fable 5.2 (mini-swe-agent harness) | low | 53.8% | $8.78 |
| Claude Fable 5.2 (mini-swe-agent harness) | medium | 60.5% | $11 |
| Claude Fable 5.2 (mini-swe-agent harness) | high | 70% | $24.3 |
| Claude Fable 5.2 (mini-swe-agent harness) | xhigh | 67.6% | $31.4 |
| Claude Fable 5.2 (mini-swe-agent harness) | max | 73.3% | $45.2 |
| Claude Opus 5.5 | max | 63.3% | $23.2 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- Claude Fable 5.2 was run in the mini-swe-agent harness, as reported by OpenAI.
Score against cost · reported by OpenAI on 17 Nov 2026 · exact values
Interpreting real biological data and running experiments to infer how a simulated system works.
- GPT-6.2 Astra
- GPT-6.2 Sol
- GPT-6 Astra
- GPT-6.1 Sol
- Claude Fable 5.2
- Claude Opus 5.5
Show data table
| Model | Effort | Accuracy (%) | Cost per task |
|---|---|---|---|
| GPT-6.2 Astra | low | 59.5% | $1.05 |
| GPT-6.2 Astra | medium | 67.6% | $1.88 |
| GPT-6.2 Astra | high | 68.1% | $2.25 |
| GPT-6.2 Astra | xhigh | 64.8% | $2.47 |
| GPT-6.2 Astra | max | 68.4% | $4.17 |
| GPT-6.2 Sol | low | 46.3% | $0.19 |
| GPT-6.2 Sol | medium | 56.5% | $0.44 |
| GPT-6.2 Sol | high | 57.6% | $0.63 |
| GPT-6.2 Sol | xhigh | 58.5% | $0.71 |
| GPT-6.2 Sol | max | 57.8% | $1.03 |
| GPT-6 Astra | max | 65.1% | $8.03 |
| GPT-6.1 Sol | max | 59.6% | $1.36 |
| Claude Fable 5.2 | high | 63.74% | $8.79 |
| Claude Opus 5.5 | max | 58.7% | $8.71 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Score against cost · reported by OpenAI on 17 Nov 2026 · exact values
Cognition's benchmark of whether changes to real codebases meet maintainers' standards for merging.
- GPT-6.2 Astra
- GPT-6.2 Sol
- GPT-6 Astra
- GPT-6.1 Sol
- Claude Fable 5.2
- Claude Opus 5.5
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.2 Astra | low | 38.1% | $1.41 |
| GPT-6.2 Astra | medium | 42.2% | $2.47 |
| GPT-6.2 Astra | high | 43.6% | $3.95 |
| GPT-6.2 Astra | xhigh | 44.1% | $4.29 |
| GPT-6.2 Astra | max | 44.2% | $5.97 |
| GPT-6.2 Sol | low | 33.1% | $0.40 |
| GPT-6.2 Sol | medium | 38.3% | $0.68 |
| GPT-6.2 Sol | high | 39.7% | $0.88 |
| GPT-6.2 Sol | xhigh | 39.8% | $0.98 |
| GPT-6.2 Sol | max | 43.8% | $1.29 |
| GPT-6 Astra | low | 31.1% | $2.44 |
| GPT-6 Astra | medium | 36.8% | $3.49 |
| GPT-6 Astra | high | 38.3% | $4.28 |
| GPT-6 Astra | xhigh | 41.4% | $4.54 |
| GPT-6 Astra | max | 42.8% | $6.68 |
| GPT-6.1 Sol | low | 25.6% | $0.34 |
| GPT-6.1 Sol | medium | 29.6% | $0.49 |
| GPT-6.1 Sol | high | 34.8% | $0.65 |
| GPT-6.1 Sol | xhigh | 32.3% | $0.70 |
| GPT-6.1 Sol | max | 39% | $1.03 |
| Claude Fable 5.2 | low | 34.2% | $2.10 |
| Claude Fable 5.2 | medium | 37.59% | $2.48 |
| Claude Fable 5.2 | high | 45.29% | $6.72 |
| Claude Fable 5.2 | xhigh | 49.11% | $14.2 |
| Claude Fable 5.2 | max | 45.65% | $44.7 |
| Claude Opus 5.5 | low | 14.7% | $0.75 |
| Claude Opus 5.5 | medium | 30.1% | $1.70 |
| Claude Opus 5.5 | high | 34.5% | $2.42 |
| Claude Opus 5.5 | xhigh | 43.4% | $5.18 |
| Claude Opus 5.5 | max | 45.5% | $12.8 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- OpenAI's chart also shows Gemini 4 Carbon, which is not in the tracker, so its results are left out.
Score against cost · reported by OpenAI on 17 Nov 2026 · exact values
Everyday tasks tailored to someone's needs, such as finding a home that fits a family's budget and commute.
- GPT-6.2 Astra
- GPT-6.2 Sol
- GPT-6 Astra
- GPT-6.1 Sol
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.2 Astra | low | 46.3% | $0.59 |
| GPT-6.2 Astra | medium | 78.9% | $1.56 |
| GPT-6.2 Astra | high | 83.1% | $2.41 |
| GPT-6.2 Astra | xhigh | 83.7% | $2.94 |
| GPT-6.2 Astra | max | 86.1% | $4.23 |
| GPT-6.2 Sol | low | 25.3% | $0.089 |
| GPT-6.2 Sol | medium | 70.3% | $0.38 |
| GPT-6.2 Sol | high | 80.8% | $0.65 |
| GPT-6.2 Sol | xhigh | 82.6% | $0.88 |
| GPT-6.2 Sol | max | 83.8% | $1.27 |
| GPT-6 Astra | low | 67.5% | $3.51 |
| GPT-6 Astra | medium | 74.3% | $5.30 |
| GPT-6 Astra | high | 76% | $6.52 |
| GPT-6 Astra | xhigh | 77.5% | $6.94 |
| GPT-6 Astra | max | 79.8% | $9.04 |
| GPT-6.1 Sol | low | 66.8% | $0.52 |
| GPT-6.1 Sol | medium | 75.5% | $0.73 |
| GPT-6.1 Sol | high | 77.1% | $0.88 |
| GPT-6.1 Sol | xhigh | 77.8% | $0.96 |
| GPT-6.1 Sol | max | 79.5% | $1.27 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Score against cost · reported by OpenAI on 17 Nov 2026 · exact values
Legal work tasks, scored by the all-pass rate gated on hallucinations.
- GPT-6.2 Astra
- GPT-6.2 Sol
- GPT-6 Astra
- GPT-6.1 Sol
- Claude Fable 5.2
- Claude Opus 5.5
Show data table
| Model | Effort | Hallucination-gated all-pass rate (%) | Cost per task |
|---|---|---|---|
| GPT-6.2 Astra | low | 2.2% | $0.86 |
| GPT-6.2 Astra | medium | 8.1% | $2.49 |
| GPT-6.2 Astra | high | 13.3% | $3.86 |
| GPT-6.2 Astra | xhigh | 12.8% | $4.31 |
| GPT-6.2 Astra | max | 15% | $6.35 |
| GPT-6.2 Sol | low | 3.1% | $0.25 |
| GPT-6.2 Sol | medium | 5% | $0.71 |
| GPT-6.2 Sol | high | 5.8% | $1.03 |
| GPT-6.2 Sol | xhigh | 6.1% | $1.23 |
| GPT-6.2 Sol | max | 11.1% | $1.92 |
| GPT-6 Astra | max | 8.6% | $13.7 |
| GPT-6.1 Sol | max | 6.9% | $2.48 |
| Claude Fable 5.2 | low | 4.2% | $9.16 |
| Claude Fable 5.2 | medium | 6.4% | $9.67 |
| Claude Fable 5.2 | high | 4.7% | $15.9 |
| Claude Fable 5.2 | xhigh | 3.9% | $24.3 |
| Claude Fable 5.2 | max | 7.2% | $39.8 |
| Claude Opus 5.5 | max | 4.2% | $17.9 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Score against cost · reported by OpenAI on 17 Nov 2026 · exact values
Computer-aided design tasks.
- GPT-6.2 Astra
- GPT-6.2 Sol
- GPT-6 Astra
- GPT-6.1 Sol
- Claude Fable 5.2
- Claude Opus 5.5
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.2 Astra | low | 42.6% | $0.98 |
| GPT-6.2 Astra | medium | 68.5% | $1.94 |
| GPT-6.2 Astra | high | 74.6% | $2.89 |
| GPT-6.2 Astra | xhigh | 77.6% | $3.36 |
| GPT-6.2 Astra | max | 82.5% | $5.43 |
| GPT-6.2 Sol | low | 23.9% | $0.15 |
| GPT-6.2 Sol | medium | 41.2% | $0.29 |
| GPT-6.2 Sol | high | 64% | $0.75 |
| GPT-6.2 Sol | xhigh | 70.4% | $1.00 |
| GPT-6.2 Sol | max | 73.1% | $1.60 |
| GPT-6 Astra | low | 20.3% | $1.14 |
| GPT-6 Astra | medium | 38.7% | $3.73 |
| GPT-6 Astra | high | 51.1% | $5.38 |
| GPT-6 Astra | xhigh | 53.9% | $6.32 |
| GPT-6 Astra | max | 62.6% | $9.71 |
| GPT-6.1 Sol | low | 13.5% | $0.19 |
| GPT-6.1 Sol | medium | 31.2% | $0.55 |
| GPT-6.1 Sol | high | 42.1% | $0.87 |
| GPT-6.1 Sol | xhigh | 45.6% | $1.05 |
| GPT-6.1 Sol | max | 52.6% | $1.61 |
| Claude Fable 5.2 | low | 26.9% | $1.89 |
| Claude Fable 5.2 | medium | 32.4% | $2.66 |
| Claude Fable 5.2 | high | 61% | $9.99 |
| Claude Fable 5.2 | xhigh | 74.1% | $23.2 |
| Claude Fable 5.2 | max | 83.5% | $50.8 |
| Claude Opus 5.5 | low | 6.3% | $0.17 |
| Claude Opus 5.5 | medium | 19.1% | $1.20 |
| Claude Opus 5.5 | high | 29.7% | $2.70 |
| Claude Opus 5.5 | xhigh | 54.5% | $9.00 |
| Claude Opus 5.5 | max | 65.3% | $20 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Score against cost · reported by OpenAI on 17 Nov 2026 · exact values
Workflow automation tasks.
- GPT-6.2 Astra
- GPT-6.2 Sol
- GPT-6 Astra
- GPT-6.1 Sol
- Claude Fable 5.2
- Claude Opus 5.5
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.2 Astra | low | 37.1% | $0.44 |
| GPT-6.2 Astra | medium | 43.8% | $0.55 |
| GPT-6.2 Astra | high | 47.9% | $0.67 |
| GPT-6.2 Astra | xhigh | 47.2% | $0.70 |
| GPT-6.2 Astra | max | 52.4% | $0.83 |
| GPT-6.2 Sol | low | 31.2% | $0.13 |
| GPT-6.2 Sol | medium | 40.2% | $0.18 |
| GPT-6.2 Sol | high | 41.2% | $0.21 |
| GPT-6.2 Sol | xhigh | 40.6% | $0.23 |
| GPT-6.2 Sol | max | 41.1% | $0.27 |
| GPT-6 Astra | low | 30.3% | $1.08 |
| GPT-6 Astra | medium | 34.1% | $1.27 |
| GPT-6 Astra | high | 37.1% | $1.44 |
| GPT-6 Astra | xhigh | 39% | $1.50 |
| GPT-6 Astra | max | 41.4% | $1.73 |
| GPT-6.1 Sol | low | 24.7% | $0.16 |
| GPT-6.1 Sol | medium | 31.7% | $0.19 |
| GPT-6.1 Sol | high | 33.2% | $0.23 |
| GPT-6.1 Sol | xhigh | 35.5% | $0.25 |
| GPT-6.1 Sol | max | 36.1% | $0.30 |
| Claude Fable 5.2 | low | 39.73% | $1.30 |
| Claude Fable 5.2 | medium | 40.18% | $1.35 |
| Claude Fable 5.2 | high | 44.29% | $1.69 |
| Claude Fable 5.2 | xhigh | 47.95% | $2.29 |
| Claude Fable 5.2 | max | 51.45% | $4.64 |
| Claude Opus 5.5 | low | 24.2% | $0.51 |
| Claude Opus 5.5 | medium | 29.5% | $0.65 |
| Claude Opus 5.5 | high | 33% | $0.71 |
| Claude Opus 5.5 | xhigh | 35.8% | $0.89 |
| Claude Opus 5.5 | max | 42.5% | $1.44 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- OpenAI's chart also shows Gemini 4 Carbon, which is not in the tracker, so its results are left out.
Score against cost · reported by OpenAI on 17 Nov 2026 · exact values
OpenAI's internal benchmark of writing functional, secure code for security-sensitive components such as serving files or handling database queries.
- GPT-6.2 Astra
- GPT-6.2 Sol
- GPT-6 Astra
- GPT-6.1 Sol
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.2 Astra | low | 54.5% | $0.78 |
| GPT-6.2 Astra | medium | 57.7% | $1.40 |
| GPT-6.2 Astra | high | 61.7% | $2.50 |
| GPT-6.2 Astra | xhigh | 63.8% | $3.12 |
| GPT-6.2 Astra | max | 65.7% | $5.26 |
| GPT-6.2 Sol | low | 43.1% | $0.16 |
| GPT-6.2 Sol | medium | 47.1% | $0.25 |
| GPT-6.2 Sol | high | 51.9% | $0.45 |
| GPT-6.2 Sol | xhigh | 54% | $0.62 |
| GPT-6.2 Sol | max | 55.6% | $0.99 |
| GPT-6 Astra | low | 41.3% | $1.10 |
| GPT-6 Astra | medium | 45.7% | $1.91 |
| GPT-6 Astra | high | 47.9% | $2.88 |
| GPT-6 Astra | xhigh | 48.7% | $3.21 |
| GPT-6 Astra | max | 46.5% | $4.91 |
| GPT-6.1 Sol | low | 36.2% | $0.13 |
| GPT-6.1 Sol | medium | 46.5% | $0.30 |
| GPT-6.1 Sol | high | 44.4% | $0.47 |
| GPT-6.1 Sol | xhigh | 46% | $0.58 |
| GPT-6.1 Sol | max | 49.7% | $0.87 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Score against cost · reported by OpenAI on 17 Nov 2026 · exact values
Producing security patches that preserve intended behavior.
- GPT-6.2 Astra
- GPT-6.2 Sol
- GPT-6 Astra
- GPT-6.1 Sol
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.2 Astra | low | 71.1% | $0.38 |
| GPT-6.2 Astra | medium | 75.6% | $0.85 |
| GPT-6.2 Astra | high | 78.8% | $1.79 |
| GPT-6.2 Astra | xhigh | 79.7% | $2.45 |
| GPT-6.2 Astra | max | 79.7% | $4.18 |
| GPT-6.2 Sol | low | 65.6% | $0.085 |
| GPT-6.2 Sol | medium | 70.5% | $0.17 |
| GPT-6.2 Sol | high | 74.1% | $0.36 |
| GPT-6.2 Sol | xhigh | 74.2% | $0.51 |
| GPT-6.2 Sol | max | 75.6% | $0.85 |
| GPT-6 Astra | low | 63% | $0.79 |
| GPT-6 Astra | medium | 67.5% | $1.35 |
| GPT-6 Astra | high | 68.8% | $2.15 |
| GPT-6 Astra | xhigh | 70.5% | $2.45 |
| GPT-6 Astra | max | 70.9% | $4.18 |
| GPT-6.1 Sol | low | 62% | $0.12 |
| GPT-6.1 Sol | medium | 64.5% | $0.22 |
| GPT-6.1 Sol | high | 67.8% | $0.37 |
| GPT-6.1 Sol | xhigh | 69.4% | $0.45 |
| GPT-6.1 Sol | max | 71% | $0.74 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Score against cost · reported by OpenAI on 26 Oct 2026 · exact values
Professional computer-use tasks, such as turning architectural drawings into a 3D model or logging an animated film shot by shot.
- GPT-6.1 Terra
- GPT-5.6 Terra
- GPT-6.1 Sol
- GPT-6 Astra
- GPT-6 Luna
- Claude Opus 5.5
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Terra | low | 55.9% | $0.16 |
| GPT-6.1 Terra | medium | 57.6% | $0.29 |
| GPT-6.1 Terra | high | 57.2% | $0.39 |
| GPT-6.1 Terra | xhigh | 58.5% | $0.66 |
| GPT-6.1 Terra | max | 60% | $1.01 |
| GPT-5.6 Terra | low | 40.2% | $0.59 |
| GPT-5.6 Terra | medium | 42.6% | $0.84 |
| GPT-5.6 Terra | high | 46.6% | $1.72 |
| GPT-5.6 Terra | xhigh | 48.5% | $2.50 |
| GPT-5.6 Terra | max | 50.7% | $3.58 |
| GPT-6.1 Sol | low | 52.4% | $0.70 |
| GPT-6.1 Sol | medium | 53.8% | $1.31 |
| GPT-6.1 Sol | high | 55.3% | $1.45 |
| GPT-6.1 Sol | xhigh | 56.5% | $1.45 |
| GPT-6.1 Sol | max | 58.6% | $2.00 |
| GPT-6 Astra | low | 53.4% | $3.55 |
| GPT-6 Astra | medium | 57.6% | $4.82 |
| GPT-6 Astra | high | 57.8% | $5.15 |
| GPT-6 Astra | xhigh | 58.3% | $5.91 |
| GPT-6 Astra | max | 59.3% | $7.24 |
| GPT-6 Luna | low | 36.3% | $0.022 |
| GPT-6 Luna | medium | 46.8% | $0.093 |
| GPT-6 Luna | high | 43.6% | $0.087 |
| GPT-6 Luna | xhigh | 47.9% | $0.093 |
| GPT-6 Luna | max | 50.9% | $0.14 |
| Claude Opus 5.5 | max | 63.2% | $8.82 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Score against cost · reported by OpenAI on 26 Oct 2026 · exact values
Visual reasoning across expert-level, multi-discipline questions.
- GPT-6.1 Terra
- GPT-5.6 Terra
- GPT-6.1 Sol
- GPT-6 Astra
- GPT-6 Luna
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Terra | low | 83.7% | $0.0038 |
| GPT-6.1 Terra | medium | 84.6% | $0.0041 |
| GPT-6.1 Terra | high | 85% | $0.0045 |
| GPT-6.1 Terra | xhigh | 85.4% | $0.0055 |
| GPT-6.1 Terra | max | 85.5% | $0.012 |
| GPT-5.6 Terra | low | 74.9% | $0.011 |
| GPT-5.6 Terra | medium | 76.4% | $0.012 |
| GPT-5.6 Terra | high | 77.5% | $0.014 |
| GPT-5.6 Terra | xhigh | 78.7% | $0.02 |
| GPT-5.6 Terra | max | 81.7% | $0.079 |
| GPT-6.1 Sol | low | 84% | $0.0076 |
| GPT-6.1 Sol | medium | 84.7% | $0.0079 |
| GPT-6.1 Sol | high | 85.8% | $0.0088 |
| GPT-6.1 Sol | xhigh | 85.8% | $0.01 |
| GPT-6.1 Sol | max | 86.3% | $0.013 |
| GPT-6 Astra | low | 85.3% | $0.038 |
| GPT-6 Astra | medium | 85.3% | $0.039 |
| GPT-6 Astra | high | 86.4% | $0.044 |
| GPT-6 Astra | xhigh | 86.5% | $0.051 |
| GPT-6 Astra | max | 86.7% | $0.065 |
| GPT-6 Luna | low | 73.5% | $0.00049 |
| GPT-6 Luna | medium | 75.1% | $0.00061 |
| GPT-6 Luna | high | 76.5% | $0.00074 |
| GPT-6 Luna | xhigh | 77.9% | $0.00095 |
| GPT-6 Luna | max | 79.9% | $0.0021 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Score against cost · reported by OpenAI on 26 Oct 2026 · exact values
Multistep tasks completed by agents using desktop apps, such as building a 3D model from a technical drawing.
- GPT-6.1 Terra
- GPT-5.6 Terra
- GPT-6.1 Sol
- GPT-6 Astra
- GPT-6 Luna
- Claude Sonnet 5.5
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Terra | low | 53.8% | $0.36 |
| GPT-6.1 Terra | medium | 66.7% | $0.50 |
| GPT-6.1 Terra | high | 68.7% | $0.51 |
| GPT-6.1 Terra | xhigh | 71.3% | $0.62 |
| GPT-6.1 Terra | max | 74.2% | $1.19 |
| GPT-5.6 Terra | low | 24.1% | $0.44 |
| GPT-5.6 Terra | medium | 27.4% | $0.59 |
| GPT-5.6 Terra | high | 37.7% | $1.19 |
| GPT-5.6 Terra | xhigh | 48.4% | $2.25 |
| GPT-5.6 Terra | max | 57.1% | $4.76 |
| GPT-6.1 Sol | low | 60.9% | $0.38 |
| GPT-6.1 Sol | medium | 73.5% | $0.65 |
| GPT-6.1 Sol | high | 75.5% | $0.90 |
| GPT-6.1 Sol | xhigh | 75.9% | $0.95 |
| GPT-6.1 Sol | max | 78% | $1.15 |
| GPT-6 Astra | low | 63.3% | $2.32 |
| GPT-6 Astra | medium | 75.4% | $4.37 |
| GPT-6 Astra | high | 78.3% | $5.76 |
| GPT-6 Astra | xhigh | 79% | $6.60 |
| GPT-6 Astra | max | 80.9% | $8.17 |
| GPT-6 Luna | low | 7.5% | $0.02 |
| GPT-6 Luna | medium | 26.3% | $0.079 |
| GPT-6 Luna | high | 39.7% | $0.14 |
| GPT-6 Luna | xhigh | 44.6% | $0.19 |
| GPT-6 Luna | max | 55.5% | $0.30 |
| Claude Sonnet 5.5 | low | 57.8% | $0.68 |
| Claude Sonnet 5.5 | medium | 65.9% | $0.93 |
| Claude Sonnet 5.5 | high | 73.3% | $1.39 |
| Claude Sonnet 5.5 | xhigh | 81% | $2.22 |
| Claude Sonnet 5.5 | max | 83.9% | $5.74 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
Error rate against cost · reported by OpenAI on 26 Oct 2026 · exact values
Answers containing at least one factual error on deliberately difficult prompts. Lower is better.
- GPT-6.1 Terra
- GPT-5.6 Terra
- GPT-6.1 Sol
- GPT-6 Astra
- GPT-6 Luna
Show data table
| Model | Effort | Answers with any factual error (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Terra | low | 16.7% | $0.024 |
| GPT-6.1 Terra | medium | 10.1% | $0.029 |
| GPT-6.1 Terra | high | 7.7% | $0.036 |
| GPT-6.1 Terra | xhigh | 5% | $0.05 |
| GPT-6.1 Terra | max | 4.3% | $0.12 |
| GPT-5.6 Terra | low | 53.6% | $0.055 |
| GPT-5.6 Terra | medium | 51.5% | $0.061 |
| GPT-5.6 Terra | high | 41.1% | $0.078 |
| GPT-5.6 Terra | xhigh | 33.9% | $0.11 |
| GPT-5.6 Terra | max | 22.3% | $0.25 |
| GPT-6.1 Sol | low | 14.7% | $0.048 |
| GPT-6.1 Sol | medium | 12% | $0.056 |
| GPT-6.1 Sol | high | 6.6% | $0.079 |
| GPT-6.1 Sol | xhigh | 5.5% | $0.099 |
| GPT-6.1 Sol | max | 4.4% | $0.12 |
| GPT-6 Astra | low | 13.3% | $0.26 |
| GPT-6 Astra | medium | 9.7% | $0.29 |
| GPT-6 Astra | high | 5.9% | $0.43 |
| GPT-6 Astra | xhigh | 4.6% | $0.55 |
| GPT-6 Astra | max | 4.2% | $0.66 |
| GPT-6 Luna | low | 44.3% | $0.0025 |
| GPT-6 Luna | medium | 31.2% | $0.0035 |
| GPT-6 Luna | high | 27.6% | $0.0047 |
| GPT-6 Luna | xhigh | 24.5% | $0.0061 |
| GPT-6 Luna | max | 18.4% | $0.013 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- Prompts are de-identified conversations where users flagged an earlier model error. They are not representative of typical usage.
Score against cost · reported by OpenAI on 26 Oct 2026 · exact values
Coding agents solving problems from the command line, such as fixing a webpage whose layout shifts as it loads.
- GPT-6.1 Terra
- GPT-5.6 Terra
- GPT-6.1 Sol
- GPT-6 Astra
- Claude Sonnet 5.5
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Terra | low | 24.8% | $0.24 |
| GPT-6.1 Terra | medium | 35.8% | $0.46 |
| GPT-6.1 Terra | high | 41.8% | $0.65 |
| GPT-6.1 Terra | xhigh | 46.4% | $0.99 |
| GPT-6.1 Terra | max | 50.3% | $1.84 |
| GPT-5.6 Terra | max | 21.5% | $5.25 |
| GPT-6.1 Sol | low | 47.1% | $0.76 |
| GPT-6.1 Sol | medium | 52.7% | $1.02 |
| GPT-6.1 Sol | high | 53% | $1.28 |
| GPT-6.1 Sol | xhigh | 53.4% | $1.28 |
| GPT-6.1 Sol | max | 55.9% | $1.98 |
| GPT-6 Astra | low | 50.6% | $4.93 |
| GPT-6 Astra | medium | 54.4% | $6.06 |
| GPT-6 Astra | high | 58.1% | $7.18 |
| GPT-6 Astra | xhigh | 57.9% | $7.45 |
| GPT-6 Astra | max | 58.2% | $10.3 |
| Claude Sonnet 5.5 | low | 20% | $0.62 |
| Claude Sonnet 5.5 | medium | 28.8% | $0.68 |
| Claude Sonnet 5.5 | high | 43% | $1.46 |
| Claude Sonnet 5.5 | xhigh | 61.5% | $4.34 |
| Claude Sonnet 5.5 | max | 70.6% | $10.4 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- GPT-5.6 Terra is shown at its published max-effort score only.
Score against cost · reported by OpenAI on 26 Oct 2026 · exact values
Scientific research tasks completed through a terminal, such as tracking cell divisions in a time-lapse video.
- GPT-6.1 Terra
- GPT-6.1 Sol
- GPT-6 Astra
- Claude Opus 5.5 with fallbacks
Show data table
| Model | Effort | Score (%) | Cost per task |
|---|---|---|---|
| GPT-6.1 Terra | low | 24.3% | $0.47 |
| GPT-6.1 Terra | medium | 34.3% | $0.95 |
| GPT-6.1 Terra | high | 39.7% | $1.24 |
| GPT-6.1 Terra | xhigh | 43.4% | $1.72 |
| GPT-6.1 Terra | max | 58.3% | $4.15 |
| GPT-6.1 Sol | low | 43.7% | $1.79 |
| GPT-6.1 Sol | medium | 47.6% | $2.34 |
| GPT-6.1 Sol | high | 51.1% | $2.76 |
| GPT-6.1 Sol | xhigh | 53.7% | $2.89 |
| GPT-6.1 Sol | max | 57% | $5.47 |
| GPT-6 Astra | low | 55.4% | $11.4 |
| GPT-6 Astra | medium | 57.4% | $12.3 |
| GPT-6 Astra | high | 62% | $14.9 |
| GPT-6 Astra | xhigh | 60.9% | $15.8 |
| GPT-6 Astra | max | 68.1% | $23.8 |
| Claude Opus 5.5 with fallbacks | max | 63.3% | $23.2 |
- Exact score and cost values from the chart data embedded in OpenAI's announcement.
- Opus 5.5 results use fallback models as reported by OpenAI; these are not standalone Opus 5.5 results.