whatmodel.sh / Claude Fable 5.1

Claude Fable 5.1

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Claude Fable 5.1 is a closed-weights language model from Anthropic, released September 2026.

84.5±0.6#4 of 719 LLMsfrom 35 benchmark results across 7 sources

$ how it compares

The LLMs ranked either side of Claude Fable 5.1, out of 828 with a score, then more from Anthropic.

#modelscorewhereRAMreleased
2Claude Opus 5.5 Anthropic87±1api $8.00/M2026-09
3GPT-6.1 Sol OpenAI85±1api $4.00/M2026-09
4Claude Fable 5.1 Anthropic85±1api $20.00/M2026-09
5Claude Sonnet 5.5 Anthropic84±1api $4.00/M2026-09
6Claude Opus 5 Anthropic83±1api $10.00/M2026-07
more from Anthropic
11Claude Fable 5 Anthropic81±1api $20.00/M2026-06
12Claude Mythos Preview (limited preview) Anthropic81±1limited preview2026-04
19Claude Opus 4.8 Anthropic78±0api $10.00/M2026-05

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▃ #3 of 300 · 28% of its score · 8 tests

Beats GPT-6 Astra, GPT-6.1 Sol here, though they rank higher overall. Trails Claude Sonnet 5.5 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Terminal-Bench 4.0 +157.9% ✎█▅▅▅▅·▅▃▃▅▅▅ beats 17/20very hard · avg 0.5%▇▇▇▇ 9.2%sharp · at its level · several runs
Arena Agent (October 2026 aggregate IPS)0.1431 IPS ✎▁▁▁▄▂▃▇█▂▂▁▃ beats 49/49avg -0.312 IPS▇▇ 6.0%sharp
SWE-bench Pro (split unspecified) lab81.2% ✎▄█·▄·▄██···▄ beats 7/9very hard · avg 7.6%▇▇ 4.8%sharp
SWE-bench Multilingual lab89.1% ✎▃··▃·▅▃▃█··▃ beats 6/9hard · avg 31%▇ 2.3%typical
Chartography with tools lab +188.4% ✎▃········▃██ beats 5/7very hard · avg 4.7%▇ 1.8%sharp
Humanity's Last Exam with tools lab +165.6% ✎▁······▁·▄·█ beats 9/10very hard · avg 14%▇ 1.7%at its level
DeepSWE v1.1 (resolved) lab67.4% ✎█·····████·█ beats 1/5hard · avg 18%▇ 1.5%at its level
Toolathlon-Verified lab77.8% ✎▃·····█···▃▃ beats 2/5hard · avg 35%▇ 0.8%blunt
coding▁▁▁▃▆██▇▆▄▃▃ #5 of 458 · 15% of its score · 5 tests

Trails Claude Sonnet 5.5 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena WebDev (Code Arena)1749.2 ✎▁▂▄▃▅█▄▇▆▄▃▁ beats 115/119avg 981▇▇ 5.3%sharp
SWE-bench Pro (split unspecified) lab81.2% ✎▄█·▄·▄██···▄ beats 7/9very hard · avg 7.6%▇▇ 4.8%sharp
SWE-bench Multilingual lab89.1% ✎▃··▃·▅▃▃█··▃ beats 6/9hard · avg 31%▇ 2.3%typical
DeepSWE v1.1 (resolved) lab67.4% ✎█·····████·█ beats 1/5hard · avg 18%▇ 1.5%at its level
Luau Leetcode fully solved (Torpedo Software)83.2% ✎▁▁▁▁·▁▂▃▅▃█▇ beats 41/49hard · avg 18%▇ 1.1%typical
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #5 of 393 * · 3.0% of its score · 1 test

Beats GPT-6 Astra, GPT-6.1 Sol here, though they rank higher overall. Trails Claude Opus 4.6, Claude Fable 5, Gemini 4 Argon (limited preview) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1501.1 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 374/379avg 1268▇ 3.0%blunt
math▁▂▃▅▆▅▄█▄▁▃▁ #4 of 398 · 28% of its score · 10 tests
testresultvs the others in its rundifficultycountswhy
FrontierMath tier 4 v287.8% ✎▁▂▁▂█▅▂▂▃▁▁▁ beats 58/63very hard · avg 0.1%▇▇▇ 7.5%sharp
MathArena ArXivMath April 2026 (40 problems)77.5% ✎▁·····▅██▄·▁ beats 19/20very hard · avg 7.2%▇▇ 4.8%sharp
FrontierMath tiers 1–3 v290.2% ✎▂··▁▁▃▄▄█▅▃▃ beats 79/82very hard · avg 1.2%▇▇ 4.7%sharp
MathArena ArXivMath June 2026 (48 problems)91.0% ✎▂···▄·██▆▆▄▂ beats 18/19very hard · avg 4.6%▇▇ 4.1%sharp
MathArena BrokenArXiv April 2026 (61 problems)80.3% ✎▂▂▆█▃▃▂▂▃··▂ beats 17/18very hard · avg 0.7%▇ 2.7%sharp · at its level · noisy
MathArena ArXivMath May 2026 (40 problems)87.5% ✎▁··▁▄█▄▁·▃·▁ beats 15/17very hard · avg 10%▇ 1.7%typical
MathArena ArXivMath August 2026, with tools (57 problems)87.7% ✎█▄·▄·······█ beats 4/5very hard · avg 4.8%▇ 1.3%sharp · at its level
MathArena BrokenArXiv August 2026, with tools (56 problems)79.8% ✎▄▄·····▄·▄·█ beats 4/5very hard · avg 5.5%▇ 0.6%at its level · noisy
2 more tests
testresultvs the others in its rundifficultycountswhy
FrontierMath: Erdős problems0.0% ✎█··········▆ beats 3/6very hard · avg 0.0%▇ 0.6%sharp · too hard for it · noisy
OTIS mock AIME 2024–2025100.0% ✎▃▃▄▃▃▃▇▇█▃▂▅ beats 193/193very hard · avg 8.5%▇ 0.1%sharp · maxed out · noisy
vision & documents▁▁▃▂▁▃▄▂▆▇█▄ #12 of 147 * · 3.0% of its score · 2 tests

Beats GPT-6.1 Sol here, though they rank higher overall. Trails Claude Opus 4.7, Muse Spark 1.2, Qwen3.8-Flash-Next here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena vision (style controlled)1287.7 ✎▁▁▂▂▂▂▄▅▅▆██ beats 133/145avg 1068▇ 2.0%blunt
Arena document (style controlled)1492.8 ✎▁▁▃▃▄▃▇█▅▇▄▅ beats 34/37avg 1335▇ 1.0%blunt
web search▂▁▂▆▄█▃▃▁▁·▁ #17 of 80 * · 1.7% of its score · 1 test

Trails GPT-4o mini (2024-07-18), Mistral Small 3.1 24B (2503), GPT-4o (2024-08-06) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Humanity's Last Exam with tools lab +165.6% ✎▁······▁·▄·█ beats 9/10very hard · avg 14%▇ 1.7%at its level
other tests11 not in a task · 31% of its score
testresultvs the others in its rundifficultycountswhy
EBR-bench (Epoch)57.1% ✎▄▂·▆█▂▆▄▆▆·▄ beats 21/23very hard · avg 0.3%▇▇▇▇ 8.8%sharp · at its level
Mystery Game Puzzles (Epoch)58.0% ✎█··▂▃▇▄█▂▃▁▁ beats 69/74very hard · avg 9.4%▇▇ 5.7%sharp · at its level · noisy
Furniture Assembly (Epoch)70.0% ✎█▆▆▆▆▂▅▂▃▂·▅ beats 26/30very hard · avg 1.2%▇▇ 5.1%sharp · at its level
Humanity's Last Exam lab60.9% ✎▂·····▂·▄▂█▄ beats 9/10very hard · avg 5.8%▇ 3.6%at its level
Chess Puzzles (Epoch)47.0% ✎█▁▁▁▁▂▁▄▂▃▁▁ beats 126/135very hard · avg 5.9%▇ 3.0%sharp · at its level · noisy
Global-MMLU lab94.0% ✎▄▄····▄▄··▄█ beats 5/6medium · avg 63%▇ 1.3%typical
SimpleQA Verified70.8% ✎▁▁▃▂▃▃▆▆█▃▂▅ beats 74/78very hard · avg 8.0%▇ 1.1%at its level
Icelandic LLM Leaderboard average (Miðeind, Sept 2026 suite)69.4% ✎▁▁▃▂▂▄▁▃▄▄▄█ beats 36/38very hard · avg 14%▇ 0.9%at its level
3 more tests
testresultvs the others in its rundifficultycountswhy
MirrorCode (Epoch)73.3% ✎█·▄▄·▄·▄·▄·█ beats 7/8very hard · avg 1.5%▇ 0.8%sharp · at its level · noisy
HealthBench lab66.7% ✎█·▄·····▄▄▄▄ beats 3/6hard · avg 29%▇ 0.7%blunt · at its level
RobloxQA v2.0 multiple choice (Torpedo Software)97.9% ✎▁▁▃▁█▄▃▃▆▂▃▂ beats 46/49easy · avg 78%▇ 0.4%maxed out

$ where to run it

Through an API

api · $20.00/M · $10 in / $50 out per 1M tokens · 1M context · docs.anthropic.com ↗ · price sourceStandard base token rate from models.dev. Provider-specific tiers, long-context surcharges, caching and promotions may differ.

$ how the score was worked out · Epoch AI — internal evaluatio… 37%, Anthropic system cards and mo… 23%, LMArena leaderboard dataset 17% and 4 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Epoch AI — internal evaluations10▇▇▇▇▇▇▇▇▇▇▇ 37%CC BY 4.0
Anthropic system cards and model announcements (lab-reported scores) · lab-reported12▇▇▇▇▇▇▇ 23%Factual vendor-reported score (not licensed content)
LMArena leaderboard dataset5▇▇▇▇▇ 17%CC BY 4.0
MathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasets6▇▇▇▇▇ 15%CC BY-SA 4.0
Terminal-Bench 4.0 official leaderboard submissions1▇ 5%Apache-2.0
Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode2▇ 2%MIT
Miðeind Icelandic LLM Leaderboard1▇ 1%CC BY 4.0
prior · pull toward the middle▇ 0%
weighted average= 84.5

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json