- input
- $0.48
- cached
- $0.096
- output
- $1.80
- Context
- 1Mtokens
- Released
- 6mo ago
- Size
- 1Tparameters
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 #53
- 1468
GPT-5.6 TerraNearby rank - 1467
ERNIE 5.1Nearby rank - 1467
MiMo-V2.5-Pro - 1466
Grok 4.5Nearby rank - 1465
GLM 5.1Nearby rank - 1455
Gemini 3.5 Flash LiteSimilar price - 1448MiMo-V2-ProPredecessor
- 1409
Qwen3.5-27BSimilar price - 1408
Mistral Medium 3.1Similar price - 1335
Nova 2 LiteSimilar price
+18 vs MiMo-V2-Pro (predecessor) · Ahead of 4 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #76
- 1484
MiniMax M3Nearby rank - 1482
Qwen3.6 Max PreviewNearby rank - 1479MiMo-V2.5-Pro
- 1474
Kimi K2.7 CodeNearby rank - 1462GPT-5.4Nearby rank
- 1435Gemini 3.5 Flash LiteSimilar price
- 1434MiMo-V2-ProPredecessor
- 1357Qwen3.5-27BSimilar price
- 1342GLM 4.6Similar price
- 1196Devstral 2 2512Similar price
+45 vs MiMo-V2-Pro (predecessor) · Ahead of 3 of 4 similarly priced models
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
Not ranked on Agent Arena yet
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 #531467
+18 vs MiMo-V2-Pro (predecessor)
- default146795% CI 1463 to 1470 · 76,793 votes
- Arena WebDevArena #761479
+45 vs MiMo-V2-Pro (predecessor)
- default147995% CI 1474 to 1484 · 22,059 votes
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.