- input
- $0.10
- cached
- $0.03
- output
- $0.40
- Context
- 1Mtokens
- Released
- 1y 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 #262
- 1448
MiMo-V2.6-FlashSimilar price - 1422
Claude Haiku 5.5Similar price - 1393
Step 3.5 FlashSimilar price - 1360
Nemotron 3 SuperSimilar price - 1326
Qwen3 30B A3BNearby rank - 1325Claude Haiku 3.5Nearby rank
- 1322
GPT-4.1 Nano - 1322
Llama 4 ScoutNearby rank - 1321
Molmo 2 8BNearby rank
Ahead of 0 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Not ranked on Arena WebDev yet
Arena Vision
Best Arena rating per model · Higher is better
Arena #139
- 1248MiMo-V2.6-FlashSimilar price
- 1160
Gemma 3 27BSimilar price - 1128Llama 4 ScoutSimilar price
- 1113Molmo 2 8BNearby rank
- 1097GPT-4o-mini (2024-07-18)Nearby rank
- 1089GPT-4.1 Nano
- 1045Molmo 72BNearby rank
- 1032Llama-3.2-90B-Vision-InstructNearby rank
- 1019
Nova Lite 1.0Similar price
Ahead of 1 of 4 similarly priced models
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
Not ranked on Agent Arena yet
ARC-AGI-2
Best score per model · Higher is better
#78 of 85
- 78.1%
DeepSeek V4.1 Flash 1017Similar price - 61.3%Claude Haiku 5.5Similar price
- 1.3%Qwen3 235B A22B Instruct 2507Similar price
- 0.0%Llama 4 ScoutSimilar price
- 0.0%
Magistral SmallNearby rank - 0.0%GPT-4.1 MiniNearby rank
- 0.0%GPT-4.1 Nano
- 0.0%GPT-4o (2024-11-20)Nearby rank
- 0.0%GPT-4o-mini (2024-07-18)Nearby rank
Ahead of 0 of 4 similarly priced models
FrontierMath-2025-02-28-Private
Best score per model · Higher is better
#50 of 58
- 8.3%GPT-5 NanoSimilar price
- 6.2%Qwen3.5-FlashSimilar price
- 1.7%DeepSeek V3Nearby rank
- 1.0%
Qwen MaxNearby rank - 1.0%GPT-4.1 Nano
- 0.3%Mistral Medium 3Nearby rank
- 0.3%Claude Haiku 3.5Nearby rank
- 0.0%Llama 4 ScoutSimilar price
Ahead of 1 of 3 similarly priced models
GPQA diamond
Best score per model · Higher is better
#137 of 161
- 89.6%Claude Haiku 5.5Similar price
- 63.8%Qwen3 14BSimilar price
- 51.8%Llama 4 ScoutSimilar price
- 49.1%Qwen2.5 72B InstructNearby rank
- 49.0%Mistral Large 2407Nearby rank
- 48.9%GPT-4.1 Nano
- 48.9%GPT-4o (2024-05-13)Nearby rank
- 48.1%Qwen-PlusNearby rank
- 47.7%Gemma 3 27BSimilar price
Ahead of 1 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#129 of 158
- 98.9%Claude Haiku 5.5Similar price
- 66.4%Qwen3 14BSimilar price
- 32.2%Mistral Medium 3Nearby rank
- 30.0%Magistral SmallNearby rank
- 28.9%GPT-4.1 Nano
- 28.1%Magistral Small 1.2Nearby rank
- 22.5%Gemma 3 27BSimilar price
- 7.8%Llama 4 ScoutSimilar price
Ahead of 2 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#87 of 87
- 42.5%DeepSeek V4.1 Flash 1017Similar price
- 23.8%Claude Haiku 5.5Similar price
- 20.3%Qwen3.5-FlashSimilar price
- 10.4%Gemma 4 31BSimilar price
- 8.3%GPT-4o-mini (2024-07-18)Nearby rank
- 6.0%GPT-4.1 Nano
Ahead of 0 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.
All published scores
- Arena TextArena #2621322
- default132295% CI 1315 to 1330 · 6,103 votes
- Arena VisionArena #1391089
- default108995% CI 1070 to 1107 · 1,211 votes
- ARC-AGI-2#78 of 850.0%
- default0.0%
- FrontierMath-2025-02-28-Private#50 of 581.0%
- default1.0%
Source:Epoch AI evaluation - GPQA diamond#137 of 16148.9%
- default48.9%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#129 of 15828.9%
- default28.9%
Source:Epoch AI evaluation - SimpleQA Verified#87 of 876.0%
- default6.0%
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.