Claude Fable 5.1vsGPT-6 Astra
SI Score, benchmarks, price and context compared, with every number sourced.
80.2
SI Score
#1 of 142 ranked models
77.5
SI Score
#3 of 142 ranked models
Pillar by pillar
Claude Fable 5.1GPT-6 Astra
87.1 Reasoning30% of score 87.1
91.5 Math15% of score 92.9
69.8 Coding40% of score 64.8
82.5 Preference15% of score 76.9
The basics
| Attribute | Claude Fable 5.1 | GPT-6 Astra |
|---|---|---|
| Input price, per 1M tokens | $10.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | $10.00OpenAI pricingOfficial Standard short-context rate; excludes Batch/Flex/cache discounts
Retrieved Oct 9, 2026 · factual citation Open source ↗ |
| Output price, per 1M tokens | $50.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | $50.00OpenAI pricingOfficial Standard short-context rate; excludes Batch/Flex/cache discounts
Retrieved Oct 9, 2026 · factual citation Open source ↗ |
| Context window | 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ |
| Released | Sep 1, 2026Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | Sep 3, 2026OpenAI API changelogPublished source fact
Retrieved Oct 9, 2026 · factual citation Open source ↗ |
| Weights | Closed | Closed |
Highlighted values are the lower price or the larger context window.
Shared benchmarks
28 in common. Best result ahead: Claude Fable 5.1 on 11, GPT-6 Astra on 12Each side shows its best published result. Results can come from different settings or harnesses, so open a row to compare like with like before reading much into a small gap.
ARC-AGI-1 (public eval) 99% 99%
Claude Fable 5.1
- low effort95.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] anthropic-claude-fable-5-1-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort96.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] anthropic-claude-fable-5-1-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort97.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] anthropic-claude-fable-5-1-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort98.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] anthropic-claude-fable-5-1-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort99%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] anthropic-claude-fable-5-1-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
GPT-6 Astra
- low effort98.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] openai-gpt-6-astra-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort98.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] openai-gpt-6-astra-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort98.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] openai-gpt-6-astra-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort99%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] openai-gpt-6-astra-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort97.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] openai-gpt-6-astra-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
ARC-AGI-1 (semi-private) 97.5% 98.5%
Claude Fable 5.1
- low effort90%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] anthropic-claude-fable-5-1-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort94.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] anthropic-claude-fable-5-1-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort96%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] anthropic-claude-fable-5-1-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort96.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] anthropic-claude-fable-5-1-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] anthropic-claude-fable-5-1-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
GPT-6 Astra
- low effort96.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] openai-gpt-6-astra-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] openai-gpt-6-astra-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort98.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] openai-gpt-6-astra-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort98.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] openai-gpt-6-astra-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] openai-gpt-6-astra-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
ARC-AGI-2 (public eval) 99.2% 97.9%
Claude Fable 5.1
- low effort86.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] anthropic-claude-fable-5-1-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort87.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] anthropic-claude-fable-5-1-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort94.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] anthropic-claude-fable-5-1-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort99.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] anthropic-claude-fable-5-1-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort98.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] anthropic-claude-fable-5-1-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
GPT-6 Astra
- low effort94.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] openai-gpt-6-astra-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort96.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] openai-gpt-6-astra-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort97.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] openai-gpt-6-astra-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort97.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] openai-gpt-6-astra-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] openai-gpt-6-astra-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
ARC-AGI-2 (semi-private) 90% 95%
Claude Fable 5.1
- low effort78.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] anthropic-claude-fable-5-1-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort86.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] anthropic-claude-fable-5-1-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort88.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] anthropic-claude-fable-5-1-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort90%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] anthropic-claude-fable-5-1-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort90%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] anthropic-claude-fable-5-1-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
GPT-6 Astra
- low effort85.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] openai-gpt-6-astra-lowPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - medium effort92.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort. [variant] openai-gpt-6-astra-mediumPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - high effort92.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] openai-gpt-6-astra-highPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - xhigh effort93.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort. [variant] openai-gpt-6-astra-xhighPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - max effort95%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] openai-gpt-6-astra-maxPublished Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
FrontierMath Tier 4 (v2) 87.8% 97.6%
Claude Fable 5.1
- max effort87.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 1, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗
GPT-6 Astra
- no reasoning82.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 30, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ - low effort87.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 30, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ - medium effort97.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 30, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ - high effort97.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 30, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ - xhigh effort97.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Aug 30, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ - max effort97.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 30, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗
FrontierMath Tiers 1–3 (v2) 90.2% 93.7%
Claude Fable 5.1
- max effort90.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 1, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗
GPT-6 Astra
- max effort93.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 30, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗
Humanity's Last Exam (Scale AI) 46.5% 54.8%
Claude Fable 5.1
- Published result46.5%Humanity’s Last ExamPotential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. [variant] Published Sep 3, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
GPT-6 Astra
- Published result54.8%Humanity’s Last ExamPotential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. [variant] Published Sep 9, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗
Humanity's Last Exam (with tools) 65% 57.2%
Claude Fable 5.1
- Published result65%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] with tools; production safeguards with fallbackPublished Sep 1, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗
GPT-6 Astra
- Published result57.2%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] with toolsPublished Sep 3, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗
LiveBench Coding: code completion 82.6% 80.4%
Claude Fable 5.1
- Published result82.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result80.4%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Coding: code generation 90.1% 80.3%
Claude Fable 5.1
- Published result90.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result80.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Coding: JavaScript 68.2% 63.6%
Claude Fable 5.1
- Published result68.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result63.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Coding: Python 70% 65%
Claude Fable 5.1
- Published result70%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result65%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Coding: TypeScript 60% 43.3%
Claude Fable 5.1
- Published result60%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result43.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Math: AMPS Hard 99% 98%
Claude Fable 5.1
- Published result99%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result98%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Math: competition math 97.1% 97.1%
Claude Fable 5.1
- Published result97.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result97.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Math: integrals 99% 100%
Claude Fable 5.1
- Published result99%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Math: olympiad 93.0% 92.2%
Claude Fable 5.1
- Published result93.0%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result92.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Math: simplify 70.2% 70.5%
Claude Fable 5.1
- Published result70.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result70.5%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: connections 99.3% 100%
Claude Fable 5.1
- Published result99.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: consecutive events 90.6% 90.6%
Claude Fable 5.1
- Published result90.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result90.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: logic with navigation 86% 88%
Claude Fable 5.1
- Published result86%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result88%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: spatial 100% 98%
Claude Fable 5.1
- Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result98%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: theory of mind 80.8% 84.6%
Claude Fable 5.1
- Published result80.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result84.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LiveBench Reasoning: zebra puzzles 100% 100%
Claude Fable 5.1
- Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
GPT-6 Astra
- Published result100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗
LMArena Text 1510.0 elo 1440.5 elo
Claude Fable 5.1
- Published result1510.0 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026
Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗
GPT-6 Astra
- Published result1440.5 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026
Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗
OTIS Mock AIME 2024–2025 100% 100%
Claude Fable 5.1
- max effort100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 1, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗
GPT-6 Astra
- max effort100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 30, 2026
Retrieved Oct 9, 2026 · CC-BY
Open source ↗
Terminal-Bench 0.1 52.6% 64.6%
Claude Fable 5.1
- Published result52.6%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] production safeguards with fallback; 0.1Published Sep 1, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗
GPT-6 Astra
- Published result64.6%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] 0.1Published Sep 3, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗
Terminal-Bench 4.0 57.9% 58.2%
Claude Fable 5.1
- Setting 157.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; maxPublished Sep 3, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 257.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; xhighPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 355.8%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] production safeguards with fallback; 4.0Published Sep 1, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ - Setting 454.5%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; highPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 553.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; mediumPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 643.3%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; lowPublished Sep 17, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗
GPT-6 Astra
- Setting 158.2%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Codex; maxPublished Sep 10, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 257.9%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] 4.0Published Sep 3, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ - Setting 357.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Codex; highPublished Sep 10, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 457.9%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Codex; xhighPublished Sep 10, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 554.2%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Codex; mediumPublished Sep 10, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ - Setting 650.6%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Codex; lowPublished Sep 10, 2026
Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗
Which should you choose?
- For coding, Claude Fable 5.1 leads by 5.0 points.
- For preference, Claude Fable 5.1 leads by 5.6 points.
- Confidence is 100% for Claude Fable 5.1 and 100% for GPT-6 Astra; sources still to report can move either score.
These follow from the numbers above. They're not a verdict on your use case.