- Context
- 1Mtokens
- Released
- 1mo 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 #131
- 1452
Gemma 4 31BSimilar price - 1448
MiMo-V2.6-FlashSimilar price - 1441
GPT-6 LunaSimilar price - 1423
Qwen3 MaxNearby rank - 1423
Mistral Large 4Nearby rank - 1422
Claude Haiku 5.5 - 1422
Qwen3 235B A22B Instruct 2507Nearby rank - 1421
R1 0528Nearby rank - 1414Claude Haiku 4.5Predecessor
- 1326Qwen3 30B A3BSimilar price
Level with Claude Haiku 4.5 (predecessor, overlapping 95% CIs) · Ahead of 1 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #38
- 1638MiMo-V2.6-FlashSimilar price
- 1609
Muse EmberSimilar price - 1608
GLM 5.2Nearby rank - 1594Claude Haiku 5.5
- 1590Qwen3.8 27BNearby rank
- 1588Gemini 3.7 FlashNearby rank
- 1577GPT-6 LunaSimilar price
- 1370Gemma 4 31BSimilar price
- 1330Claude Haiku 4.5Predecessor
+264 vs Claude Haiku 4.5 (predecessor) · Ahead of 2 of 4 similarly priced models
Arena Vision
Best Arena rating per model · Higher is better
Not ranked on Arena Vision yet
Arena Search
Best Arena rating per model · Higher is better
Not ranked on Arena Search yet
Arena Document
Best Arena rating per model · Higher is better
Not ranked on Arena Document yet
Agent Arena
Best IPS score per model · Higher is better
Arena #29
- +0.020DeepSeek V4.1 Flash 1017Similar price
- +0.017Muse EmberSimilar price
- +0.016GPT-6 LunaSimilar price
- +0.010GLM 5.3Nearby rank
- +0.006
Kimi K3Nearby rank - +0.005Claude Haiku 5.5
- +0.005
Hy4 previewNearby rank - +0.002GLM 5.2Nearby rank
- -0.000MiMo-V2.6-FlashSimilar price
Ahead of 0 of 4 similarly priced models
ARC-AGI-2
Best score per model · Higher is better
#33 of 85
- 78.1%DeepSeek V4.1 Flash 1017Similar price
- 61.4%DeepSeek V4 Flash 0731Nearby rank
- 61.4%
Grok 4.7Nearby rank - 61.3%Claude Haiku 5.5
- 61.3%DeepSeek V4 Pro 0813Nearby rank
- 60.4%Claude Sonnet 4.6Nearby rank
- 59.3%GPT-6 LunaSimilar price
- 4.0%Claude Haiku 4.5Predecessor
- 1.3%Qwen3 235B A22B Instruct 2507Similar price
- 0.0%Llama 4 ScoutSimilar price
+57.2 pts vs Claude Haiku 4.5 (predecessor) · Ahead of 3 of 4 similarly priced models
FrontierMath-Tier-4-v2-Private
Best score per model · Higher is better
#23 of 72
- 56.1%GPT-6 LunaSimilar price
- 49.0%GPT-5.4Nearby rank
- 46.3%Qwen3.8 MaxNearby rank
- 46.3%Claude Haiku 5.5
- 46.3%DeepSeek V4.1 Flash 1017Similar price
- 46.3%Muse Spark 1.3Nearby rank
- 24.4%DeepSeek V4 Flash 0731Similar price
- 2.4%GPT-5 NanoSimilar price
Ahead of 2 of 4 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#22 of 87
- 78.9%GPT-6 LunaSimilar price
- 78.6%GPT-5.4Nearby rank
- 75.1%Claude Haiku 5.5
- 74.7%Qwen3.8 MaxNearby rank
- 74.4%Muse Spark 1.3Nearby rank
- 71.2%DeepSeek V4.1 Flash 1017Similar price
- 20.4%Qwen3.6 35B A3BSimilar price
- 0.7%GPT-4o-mini (2024-07-18)Similar price
Ahead of 3 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#47 of 161
- 93.2%DeepSeek V4.1 Flash 1017Similar price
- 90.5%GPT-6 LunaSimilar price
- 89.9%GLM 5.1Nearby rank
- 89.8%DeepSeek V4.1 FlashNearby rank
- 89.6%Claude Haiku 5.5
- 89.4%Gemini 3 Flash PreviewNearby rank
- 89.3%Grok 4.20 (Reasoning)Nearby rank
- 75.8%Gemma 4 31BSimilar price
- 71.2%Claude Haiku 4.5Predecessor
- 61.7%Qwen3 30B A3BSimilar price
+18.4 pts vs Claude Haiku 4.5 (predecessor) · Ahead of 2 of 4 similarly priced models
Humanity's Last Exam
Best score per model · Higher is better
#12 of 34
- 34.4%Claude Opus 4.6Nearby rank
- 31.6%GPT-5 ProNearby rank
- 30.1%Claude Haiku 5.5
- 27.8%GPT-5.2Nearby rank
- 25.3%GPT-5Nearby rank
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#19 of 158
- 99.4%DeepSeek V4.1 Flash 1017Similar price
- 99.2%Muse Spark 1.3Nearby rank
- 99.2%Grok 4.6Nearby rank
- 98.9%Claude Haiku 5.5
- 98.9%Claude Opus 5Nearby rank
- 98.9%Gemini 3.8 FlashNearby rank
- 98.9%GPT-6 LunaSimilar price
- 73.3%Gemma 4 31BSimilar price
- 66.7%Claude Haiku 4.5Predecessor
- 62.8%Qwen3 30B A3BSimilar price
+32.2 pts vs Claude Haiku 4.5 (predecessor) · Ahead of 2 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#72 of 87
- 42.5%DeepSeek V4.1 Flash 1017Similar price
- 41.4%GPT-6 LunaSimilar price
- 26.0%GPT-4o (2024-08-06)Nearby rank
- 25.4%Qwen3.5 PlusNearby rank
- 23.8%Claude Haiku 5.5
- 21.6%GPT-5 MiniNearby rank
- 20.3%Qwen3.5-FlashSimilar price
- 13.2%Claude Haiku 4.5Predecessor
- 10.4%Gemma 4 31BSimilar price
+10.6 pts vs Claude Haiku 4.5 (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
OTIS Mock AIME 2024-2025
Score by reasoning effort · Higher is better
All published scores
- Arena TextArena #1311422
Level with Claude Haiku 4.5 (predecessor, overlapping 95% CIs)
- high142295% CI 1416 to 1429 · 13,239 votes
- Arena WebDevArena #381594
+264 vs Claude Haiku 4.5 (predecessor)
- high159495% CI 1585 to 1602 · 6,549 votes
- Agent ArenaArena #29+0.005
- high+0.00595% CI -0.006 to +0.015 · 4,460,773 observations
- ARC-AGI-2#33 of 8561.3%
+57.2 pts vs Claude Haiku 4.5 (predecessor)
- low2.8%
- medium9.4%
- high30.7%
- xhigh61.3%
- FrontierMath-Tier-4-v2-Private#23 of 7246.3%
- max46.3%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#22 of 8775.1%
- max75.1%
Source:Epoch AI evaluation - GPQA diamond#47 of 16189.6%
+18.4 pts vs Claude Haiku 4.5 (predecessor)
- max89.6%
Source:Epoch AI evaluation - Humanity's Last Exam#12 of 3430.1%
- unknown30.1%
- OTIS Mock AIME 2024-2025#19 of 15898.9%
+32.2 pts vs Claude Haiku 4.5 (predecessor)
- high97.2%
- xhigh98.9%
Source:Epoch AI evaluation - SimpleQA Verified#72 of 8723.8%
+10.6 pts vs Claude Haiku 4.5 (predecessor)
- max23.8%
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.