- input
- $0.20
- output
- $0.40
- Context
- 262Ktokens
- Released
- 7mo ago
- Size
- 32.7Bparameters
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 #78
- 1454
Hy3Nearby rank - 1453
GPT-5.6 LunaNearby rank - 1452
Gemma 4 31B - 1450
Claude Opus 4.1Nearby rank - 1450
Kimi K2.5Nearby rank - 1409Hy3 previewSimilar price
- 1387
Solar Pro 4Similar price - 1365Gemma 3 27BPredecessor
- 1352gpt-oss-120bSimilar price
- 1251
Command R (08-2024)Similar price
+86 vs Gemma 3 27B (predecessor) · Ahead of 4 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #117
- 1664
DeepSeek V4.1 Flash 1017Similar price - 1609
Muse EmberSimilar price - 1389Claude Opus 4.1Nearby rank
- 1386
MiniMax M2.5Nearby rank - 1370Gemma 4 31B
- 1369Solar Pro 4Similar price
- 1362DeepSeek V3.2Nearby rank
- 1358Hy3 previewSimilar price
Ahead of 0 of 4 similarly priced models
Arena Vision
Best Arena rating per model · Higher is better
Arena #39
- 1266GPT-5.6 TerraNearby rank
- 1266Gemini 3.5 Flash LiteNearby rank
- 1265Gemma 4 31B
- 1265Kimi K2.6Nearby rank
- 1263
Grok 4.6Nearby rank - 1248
MiMo-V2.6-FlashSimilar price - 1160Gemma 3 27BPredecessor
- 1128Llama 4 ScoutSimilar price
- 1127
Mistral Small 3.1 24BSimilar price - 1097GPT-4o-mini (2024-07-18)Similar price
+105 vs Gemma 3 27B (predecessor) · Ahead of 4 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
Arena #31
- 1460GPT-5.6 LunaSimilar price
- 1459Gemini 3.5 FlashNearby rank
- 1454Gemini 3.6 FlashNearby rank
- 1452Gemma 4 31B
- 1451Gemini 3 Pro PreviewNearby rank
- 1450Kimi K2.6Nearby rank
Ahead of 0 of 1 similarly priced model
Agent Arena
Best IPS score per model · Higher is better
Not ranked on Agent Arena yet
GPQA diamond
Best score per model · Higher is better
#98 of 161
- 93.2%DeepSeek V4.1 Flash 1017Similar price
- 89.6%Claude Haiku 5.5Similar price
- 76.3%R1 0528Nearby rank
- 76.3%Claude Opus 4Nearby rank
- 75.8%Gemma 4 31B
- 75.8%gpt-oss-120bSimilar price
- 75.0%GPT-5 MiniNearby rank
- 61.7%
Qwen3 30B A3BSimilar price - 47.7%Gemma 3 27BPredecessor
+28.0 pts vs Gemma 3 27B (predecessor) · Ahead of 1 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#89 of 158
- 99.4%DeepSeek V4.1 Flash 1017Similar price
- 98.9%Claude Haiku 5.5Similar price
- 88.9%gpt-oss-120bSimilar price
- 77.8%Claude Sonnet 4.5Nearby rank
- 73.3%
Qwen3 MaxNearby rank - 73.3%Gemma 4 31B
- 71.1%Claude Sonnet 4Nearby rank
- 71.1%Gemini 3.5 Flash LiteNearby rank
- 62.8%Qwen3 30B A3BSimilar price
- 22.5%Gemma 3 27BPredecessor
+50.8 pts vs Gemma 3 27B (predecessor) · Ahead of 1 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#85 of 87
- 42.5%DeepSeek V4.1 Flash 1017Similar price
- 41.0%
GLM 5.3Similar price - 23.8%Claude Haiku 5.5Similar price
- 11.7%GPT-5 NanoNearby rank
- 11.7%GPT-5.4 NanoNearby rank
- 10.4%Gemma 4 31B
- 8.3%GPT-4o-mini (2024-07-18)Similar price
- 6.0%GPT-4.1 NanoNearby rank
Ahead of 1 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 #781452
+86 vs Gemma 3 27B (predecessor)
- default145295% CI 1444 to 1459 · 6,130 votes
- Arena WebDevArena #1171370
- default137095% CI 1364 to 1376 · 16,462 votes
- Arena VisionArena #391265
+105 vs Gemma 3 27B (predecessor)
- default126595% CI 1259 to 1270 · 41,787 votes
- Arena DocumentArena #311452
- default145295% CI 1445 to 1459 · 15,431 votes
- GPQA diamond#98 of 16175.8%
+28.0 pts vs Gemma 3 27B (predecessor)
- minimal75.8%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#89 of 15873.3%
+50.8 pts vs Gemma 3 27B (predecessor)
- minimal73.3%
Source:Epoch AI evaluation - SimpleQA Verified#85 of 8710.4%
- default10.4%
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.