- Context
- 1Mtokens
- Released
- 2mo ago
Cost/1M tokens
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Arena leaderboards and other sourced evaluations appear below; missing scores are not zero.
How it ranks
Against its predecessor, similarly priced models and the models ranked around it.
DeepSWE 1.1
Best pass@1 per model · Higher is better
Not evaluated in DeepSWE 1.1
Arena Text
Best Arena rating per model · Higher is better
Arena #7
- 1504
Claude Fable 5Predecessor - 1503Claude Opus 4.6Similar price
- 1503Claude Fable 5.1
- 1501Claude Opus 4.7Nearby rank
- 1497
Gemini 3.8 FlashNearby rank - 1481
GPT-5.5Similar price - 1474GPT-6 AstraSimilar price
- 1450Claude Opus 4.1Similar price
Level with Claude Fable 5 (predecessor, overlapping 95% CIs) · Ahead of 3 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #7
- 1836Claude Fable 5.2Similar price
- 1764GPT-6 AstraSimilar price
- 1743GPT-6.1 SolNearby rank
- 1742Claude Fable 5.1
- 1723
Muse Wonder FullNearby rank - 1691Claude Opus 5Nearby rank
- 1625Claude Fable 5Predecessor
- 1512GPT-5.5Similar price
- 1389Claude Opus 4.1Similar price
+117 vs Claude Fable 5 (predecessor) · Ahead of 2 of 4 similarly priced models
Arena Vision
Best Arena rating per model · Higher is better
Arena #15
- 1309Claude Fable 5Predecessor
- 1300Claude Opus 4.7Similar price
- 1299Claude Opus 4.6Similar price
- 1291Muse Spark 1.3Nearby rank
- 1289Gemini 3 Pro PreviewNearby rank
- 1289Claude Fable 5.1
- 1288GPT-5.6 SolNearby rank
- 1286Claude Opus 4.8Nearby rank
- 1285GPT-5.5Similar price
- 1283GPT-6 AstraSimilar price
-20 vs Claude Fable 5 (predecessor) · Ahead of 0 of 4 similarly priced models
Arena Search
Best Arena rating per model · Higher is better
Arena #7
- 1245GPT-6 AstraSimilar price
- 1229Claude Fable 5Predecessor
- 1227
Qwen3.8 MaxNearby rank - 1227Claude Fable 5.1
- 1213Claude Opus 5Similar price
- 1213Claude Opus 5.5Nearby rank
- 1210Claude Opus 4.7Similar price
- 1194Claude Opus 4.8Similar price
Level with Claude Fable 5 (predecessor, overlapping 95% CIs) · Ahead of 2 of 4 similarly priced models
Arena Document
Best Arena rating per model · Higher is better
Arena #2
- 1500Claude Fable 5Predecessor
- 1498Claude Fable 5.1
- 1497Claude Opus 4.6Similar price
- 1494Claude Opus 4.7Similar price
- 1481GPT-5.5Similar price
- 1474GPT-6 AstraSimilar price
Level with Claude Fable 5 (predecessor, overlapping 95% CIs) · Ahead of 1 of 4 similarly priced models
Agent Arena
Best IPS score per model · Higher is better
Arena #5
- +0.304Claude Fable 5.2Similar price
- +0.170Gemini 4 CarbonNearby rank
- +0.160Claude Sonnet 5.5Nearby rank
- +0.148Claude Fable 5.1
- +0.145GPT-6 AstraSimilar price
- +0.125GPT-6.1 SolNearby rank
- +0.073Claude Fable 5Predecessor
- +0.072Claude Opus 5Similar price
+0.075 vs Claude Fable 5 (predecessor) · Ahead of 1 of 3 similarly priced models
ARC-AGI-2
Best score per model · Higher is better
#8 of 85
- 95.0%GPT-6 AstraSimilar price
- 93.8%Claude Fable 5.2Similar price
- 92.5%GPT-5.6 SolNearby rank
- 91.3%Gemini 4 ArgonNearby rank
- 90.0%Claude Fable 5.1
- 89.6%GPT-6 SolNearby rank
- 89.2%Claude Fable 5Predecessor
- 85.0%GPT-5.5Similar price
- 4.9%o3 ProSimilar price
+0.8 pts vs Claude Fable 5 (predecessor) · Ahead of 2 of 4 similarly priced models
FrontierMath-Tier-4-v2-Private
Best score per model · Higher is better
#9 of 72
- 100.0%Claude Fable 5.2Similar price
- 97.6%GPT-6 AstraSimilar price
- 90.2%Claude Fable 5Predecessor
- 90.0%GPT-6 SolNearby rank
- 87.8%Claude Fable 5.1
- 82.9%GPT-5.6 SolNearby rank
- 80.5%Claude Sonnet 5.5Nearby rank
- 72.5%GPT-5.5Similar price
- 2.4%Claude Opus 4.1Similar price
-2.4 pts vs Claude Fable 5 (predecessor) · Ahead of 2 of 4 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#7 of 87
- 95.1%Claude Fable 5.2Similar price
- 93.7%GPT-6 AstraSimilar price
- 90.9%GPT-6.1 TerraNearby rank
- 90.5%Gemini 4 CarbonNearby rank
- 90.2%Claude Fable 5.1
- 89.8%GPT-6 SolNearby rank
- 89.1%GPT-5.6 SolNearby rank
- 87.0%Claude Fable 5Predecessor
- 85.3%GPT-5.5Similar price
- 12.6%Claude Opus 4.1Similar price
+3.2 pts vs Claude Fable 5 (predecessor) · Ahead of 2 of 4 similarly priced models
Humanity's Last Exam
Best score per model · Higher is better
#2 of 34
- 54.8%GPT-6 AstraSimilar price
- 46.5%Claude Fable 5.1
- 46.4%Gemini 3.1 Pro PreviewNearby rank
- 46.1%Claude Sonnet 5.5Nearby rank
- 36.2%Claude Opus 4.7Similar price
- 34.4%Claude Opus 4.6Similar price
- 7.9%Claude Opus 4.1Similar price
Ahead of 3 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#1 of 158
- 100.0%Claude Fable 5Predecessor
- 100.0%Claude Fable 5.1
- 100.0%Claude Opus 5.5Nearby rank
- 100.0%Claude Sonnet 5.5Nearby rank
- 100.0%GPT-6 AstraSimilar price
- 99.7%Claude Fable 5.2Similar price
- 84.4%GPT-5.5Similar price
- 68.9%Claude Opus 4.1Similar price
Level with Claude Fable 5 (predecessor) · Ahead of 3 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#8 of 87
- 94.0%Claude Fable 5.2Similar price
- 75.6%GPT-6 AstraSimilar price
- 73.5%Gemini 3.1 Pro PreviewNearby rank
- 72.2%Claude Opus 5.5Nearby rank
- 70.8%Claude Fable 5.1
- 70.7%Claude Fable 5Predecessor
- 69.7%Gemini 3.8 FlashNearby rank
- 63.0%GPT-5.5Similar price
- 59.9%Claude Opus 5Similar price
+0.1 pts vs Claude Fable 5 (predecessor) · Ahead of 2 of 4 similarly priced models
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
Reasoning effort
ARC-AGI-2
Score by reasoning effort · Higher is better
All published scores
- Arena TextArena #71503
Level with Claude Fable 5 (predecessor, overlapping 95% CIs)
- max150395% CI 1497 to 1508 · 20,087 votes
- Arena WebDevArena #71742
+117 vs Claude Fable 5 (predecessor)
- max174295% CI 1734 to 1750 · 9,756 votes
- Arena VisionArena #151289
-20 vs Claude Fable 5 (predecessor)
- max128995% CI 1281 to 1298 · 6,296 votes
- Arena SearchArena #71227
Level with Claude Fable 5 (predecessor, overlapping 95% CIs)
- high122795% CI 1220 to 1234 · 33,769 votes
- Arena DocumentArena #21498
Level with Claude Fable 5 (predecessor, overlapping 95% CIs)
- max149895% CI 1483 to 1514 · 1,453 votes
- Agent ArenaArena #5+0.148
+0.075 vs Claude Fable 5 (predecessor)
- max+0.14895% CI +0.128 to +0.169 · 2,434,457 observations
- ARC-AGI-2#8 of 8590.0%
+0.8 pts vs Claude Fable 5 (predecessor)
- low78.3%
- medium86.3%
- high88.8%
- xhigh90.0%
- max90.0%
- FrontierMath-Tier-4-v2-Private#9 of 7287.8%
-2.4 pts vs Claude Fable 5 (predecessor)
- max87.8%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#7 of 8790.2%
+3.2 pts vs Claude Fable 5 (predecessor)
- max90.2%
Source:Epoch AI evaluation - Humanity's Last Exam#2 of 3446.5%
- xhigh46.5%
- OTIS Mock AIME 2024-2025#1 of 158100.0%
Level with Claude Fable 5 (predecessor)
- max100.0%
Source:Epoch AI evaluation - SimpleQA Verified#8 of 8770.8%
+0.1 pts vs Claude Fable 5 (predecessor)
- max70.8%
Source:Epoch AI evaluation
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.