- input
- $0.2375
- cached
- $0.19
- output
- $8.7856
- Context
- 1Mtokens
- Released
- 2w ago
- Size
- 2.8Tparameters
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 #24
- 1496
Muse Spark 1.3Similar price - 1487
Kimi K3Predecessor - 1485
GPT-5.6 SolNearby rank - 1484
Qwen3.8 MaxNearby rank - 1483Kimi K3.1 Pro
- 1483
Gemini 3.6 FlashNearby rank - 1483
GLM 5.3Nearby rank - 1466
Grok 4.5Similar price - 1465GLM 5.1Similar price
- 1414
Claude Haiku 4.5Similar price
Level with Kimi K3 (predecessor, overlapping 95% CIs) · Ahead of 3 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #11
- 1723Muse Wonder FullNearby rank
- 1691Claude Opus 5Nearby rank
- 1688Kimi K3.1 Pro
- 1682Gemini 4 ArgonNearby rank
- 1679GPT-6.1 TerraSimilar price
- 1658Kimi K3Predecessor
- 1655Muse Spark 1.3Similar price
- 1515
Qwen3.7 MaxSimilar price - 1508GLM 5.1Similar price
+30 vs Kimi K3 (predecessor) · Ahead of 3 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
Agent Arena
Best IPS score per model · Higher is better
Arena #15
- +0.120GPT-6.1 TerraSimilar price
- +0.069GPT-6 SolNearby rank
- +0.053
Hy4Nearby rank - +0.049Kimi K3.1 Pro
- +0.046GPT-5.6 SolNearby rank
- +0.026Grok 4.7Similar price
- +0.022Muse Spark 1.3Similar price
- +0.006Kimi K3Predecessor
- -0.072Qwen3.7 MaxSimilar price
+0.043 vs Kimi K3 (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.
All published scores
- Arena TextArena #241483
Level with Kimi K3 (predecessor, overlapping 95% CIs)
- max148395% CI 1472 to 1494 · 3,443 votes
- Arena WebDevArena #111688
+30 vs Kimi K3 (predecessor)
- max168895% CI 1678 to 1697 · 4,916 votes
- Agent ArenaArena #15+0.049
+0.043 vs Kimi K3 (predecessor)
- max+0.04995% CI +0.038 to +0.060 · 6,446,421 observations
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.