Claw-Eval Avg

Claw-Eval average score - agentic coding evaluation.

Category

Agentic Coding

Max Score

100.0

Score Type

percent

Active

Yes

Model Scores

Scores for Claw-Eval Avg

Model Score Date Verified
Qwen3.6-35B-A3B
82.81%
16.04.2026 Verified
GLM 5.1 Thinking
75.28%
11.06.2026 Unverified
Kimi K2.6
73.78%
11.06.2026 Unverified
Gemma4-31B-it
57.47%
16.04.2026 Unverified
Qwen3.5-35B-A3B
78.67%
16.04.2026 Unverified
Gemma4-26B-A4B
70.39%
16.04.2026 Unverified
Qwen3.6-27B
87.45%
22.04.2026 Verified
Qwen3.5-397B-A17B
85.32%
22.04.2026 Unverified
Claude 4.5 Opus
92.72%
22.04.2026 Unverified
Claude Sonnet 4.6
82.31%
11.06.2026 Unverified
Qwen3.5-27B
77.29%
16.04.2026 Unverified
Ornith-1.0-9B
75.78%
25.06.2026 Verified
Qwen3.5-9B
63.36%
25.06.2026 Unverified
Gemma4-12B
37.39%
25.06.2026 Unverified
Ornith-1.0-35B
84.19%
25.06.2026 Verified
Qwen3.7-Plus
72.02%
18.08.2026 Unverified
Opus4.6 Max
65.24%
18.08.2026 Unverified
Claude Opus 4.7
86.45%
11.06.2026 Unverified
MiniMax-M3
90.09%
11.06.2026 Verified
Gemini 3.1 Pro
69.13%
11.06.2026 Unverified
Claude Opus 4.6
100.00%
23.08.2026 Verified
Kimi K2.5
91.22%
23.08.2026 Verified
LFM2.5-2.6B
20.83%
— Verified
Qwen3.5-2B
28.61%
— Verified
Qwen3.5-4B
61.36%
— Verified
granite-4.2-3B
71.89%
— Verified
Nemotron-3-Nano-4B
38.90%
— Verified
Gemma4-E4B
44.17%
— Verified
LFM2.5-8B-A1B
2.70
— Verified
MiniMax-M2.7
58.97%
11.06.2026 Unverified
Qwen3.8-27B
68.01%
18.08.2026 Verified
Muse Glimmer-30B
65.24%
18.08.2026 Unverified
DeepSeek V4 Pro
69.89%
11.06.2026 Unverified
GPT-5.4
94.98%
23.08.2026 Verified
Qwen3.8-Flash-Next
72.40%
26.08.2026 Verified
Claude-Opus-4.6 (Max)
65.24%
26.08.2026 Unverified
MiniCPM5-2B
70.89%
— Verified
Gemma4-E2B
35.88%
— Verified