- input
- $0.15
- cached
- $0.0375
- output
- $1.875
- Context
- 1Mtokens
- Released
- 3mo ago
- Size
- 27Bparameters
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 #112
- 1480
MiMo-V2.6-ProSimilar price - 1475
DeepSeek V4.1 FlashSimilar price - 1434
GLM 5V TurboNearby rank - 1434MiMo-V2.5Nearby rank
- 1433
Qwen3.8 27B - 1433
Gemini 3.1 Flash Lite PreviewSimilar price - 1432
o3Nearby rank - 1409Qwen3.5-27BPredecessor
- 1405
Inkling SmallSimilar price
+25 vs Qwen3.5-27B (predecessor) · Ahead of 1 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #39
- 1624MiMo-V2.6-ProSimilar price
- 1621DeepSeek V4.1 FlashSimilar price
- 1608GLM 5.2Nearby rank
- 1594
Claude Haiku 5.5Nearby rank - 1590Qwen3.8 27B
- 1588Gemini 3.7 FlashNearby rank
- 1585
MiniMax M3.1 FlashNearby rank - 1408Inkling SmallSimilar price
- 1357Qwen3.5-27BPredecessor
- 1256Gemini 3.1 Flash Lite PreviewSimilar price
+233 vs Qwen3.5-27B (predecessor) · Ahead of 2 of 4 similarly priced models
Arena Vision
Best Arena rating per model · Higher is better
Arena #61
- 1263DeepSeek V4.1 FlashSimilar price
- 1247MiMo-V2.6-ProSimilar price
- 1246Qwen3.5 397B A17BNearby rank
- 1245
Step 5 PreviewNearby rank - 1243Qwen3.8 27B
- 1242GPT-5.2Nearby rank
- 1242Gemma 4 26B A4BNearby rank
- 1235Gemini 3.1 Flash Lite PreviewSimilar price
- 1216Qwen3.5-27BPredecessor
- 1208Inkling SmallSimilar price
+27 vs Qwen3.5-27B (predecessor) · Ahead of 1 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
Arena #43
- +0.053
Hy4Similar price - +0.024MiMo-V2.6-ProSimilar price
- -0.045Gemini 3.1 Pro PreviewNearby rank
- -0.046
Qwen3.8 Flash NextNearby rank - -0.048Qwen3.8 27B
- -0.054
Mistral Large 4Nearby rank - -0.059
Beam 1.0 501B A23BNearby rank - -0.105MiniMax M3Similar price
- -0.181Inkling SmallSimilar price
Ahead of 2 of 4 similarly priced models
ARC-AGI-2
Best score per model · Higher is better
#43 of 85
- 72.9%DeepSeek V4.1 FlashSimilar price
- 52.9%GPT-5.2Nearby rank
- 52.6%
Grok 4.5Nearby rank - 42.4%Qwen3.8 27B
- 40.1%Inkling SmallSimilar price
- 37.6%Claude Opus 4.5Nearby rank
- 4.4%GPT-5 MiniSimilar price
- 0.0%
Llama 4 MaverickSimilar price
Ahead of 3 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.
Reasoning effort
ARC-AGI-2
Score by reasoning effort · Higher is better
All published scores
- Arena TextArena #1121433
+25 vs Qwen3.5-27B (predecessor)
- default143395% CI 1429 to 1438 · 32,659 votes
- Arena WebDevArena #391590
+233 vs Qwen3.5-27B (predecessor)
- default159095% CI 1584 to 1596 · 20,791 votes
- Arena VisionArena #611243
+27 vs Qwen3.5-27B (predecessor)
- default124395% CI 1235 to 1251 · 9,632 votes
- Agent ArenaArena #43-0.048
- default-0.04895% CI -0.056 to -0.039 · 8,433,660 observations
- ARC-AGI-2#43 of 8542.4%
- none1.5%
- low22.8%
- medium13.2%
- xhigh42.4%
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.