- input
- $0.00
- output
- $0.00
- Context
- 1Mtokens
- Released
- 1w 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 #151
- 1526
Gemini 4 CarbonSimilar release date - 1511
Muse WonderSimilar release date - 1483
Kimi K3.1 ProSimilar release date - 1435
Beam 1.0 501B A23BSimilar release date - 1414
Claude Haiku 4.5Nearby rank - 1413
Qwen3 VL 235B A22B InstructNearby rank - 1412
Inkling 2 Small - 1411
GLM 4.5Nearby rank - 1409Gemini 2.5 FlashNearby rank
Ahead of 0 of 4 models released around the same time
Arena WebDev
Best Arena rating per model · Higher is better
Arena #22
- 1836Claude Fable 5.2Similar release date
- 1768Gemini 4 CarbonSimilar release date
- 1679
GPT-6.1 TerraSimilar release date - 1655Muse Spark 1.3Nearby rank
- 1649Muse WonderNearby rank
- 1646Inkling 2 Small
- 1641
Grok 4.7Nearby rank - 1638
MiMo-V2.6-FlashNearby rank - 1609Muse EmberSimilar release date
Ahead of 1 of 4 models released around the same time
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
Agent Arena
Best IPS score per model · Higher is better
Arena #18
- +0.304Claude Fable 5.2Similar release date
- +0.170Gemini 4 CarbonSimilar release date
- +0.053
Hy4Similar release date - +0.046GPT-5.6 SolNearby rank
- +0.026Grok 4.7Nearby rank
- +0.025Inkling 2 Small
- +0.024MiMo-V2.6-ProNearby rank
- +0.023Gemini 3.8 FlashNearby rank
- +0.017Muse EmberSimilar release date
Ahead of 0 of 4 models released around the same time
ARC-AGI-2
Best score per model · Higher is better
#19 of 85
- 94.2%Gemini 4 CarbonSimilar release date
- 94.2%GPT-6.1 SolSimilar release date
- 93.8%Claude Fable 5.2Similar release date
- 83.9%Claude Sonnet 5.5Nearby rank
- 83.3%GPT-5.4 ProNearby rank
- 81.7%Inkling 2 Small
- 78.1%
DeepSeek V4.1 Flash 1017Similar release date - 77.1%Gemini 3.1 Pro PreviewNearby rank
Ahead of 1 of 4 models released around the same time
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 #1511412
- default141295% CI 1400 to 1424 · 2,668 votes
- Arena WebDevArena #221646
- default164695% CI 1627 to 1666 · 983 votes
- Agent ArenaArena #18+0.025
- default+0.02595% CI +0.010 to +0.040 · 1,511,880 observations
- ARC-AGI-2#19 of 8581.7%
- xhigh81.7%
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.