open god mode ▮

Open-weights LLM ranking — agentic

scored as 100% swe_bench_verified (renormalized when signals are missing) — methodology

# model score org params ctx elo $/M out prov
1 kimi-k2-0905 ● 100.0 moonshotai 1000B (A32B) 256k — $2.50 2
2 qwen3-coder-480b-a35b ● 92.9 qwen 480B (A35B) 1024k — $1.00 6
3 glm-4.6 ● 85.7 zai-org 355B (A32B) 198k — $1.74 5
4 kimi-k2-instruct ● 78.6 moonshotai 1000B (A32B) 128k — $2.30 1
5 glm-4.5 ● 71.4 zai-org 355B (A32B) 128k — $2.20 1
6 kimi-k2-thinking ● 64.3 moonshotai 1000B (A32B) 256k — $2.50 2
7 minimax-m2 ● 57.1 minimax 229B (A10B) 200k — $1.02 3
8 qwen3-coder-30b-a3b ● 50.0 qwen 30.5B (A3.3B) 160k — $0.27 5
9 deepseek-v3.2 ● 42.9 deepseek-ai 671B (A37B) 160k — $0.34 17
10 devstral-small-2512 ● 35.7 mistralai 24B — — — —
11 devstral-2-2512 ● 28.6 mistralai 123B 256k — $2.00 1
12 qwen2.5-coder-32b ● 21.4 qwen 32.8B 125k — $1.00 1
13 deepseek-v3 ● 14.3 deepseek-ai 671B (A37B) 128k — $0.80 3
14 devstral-small-2507 ● 7.1 mistralai 24B — — — —
15 gpt-oss-120b ● — openai 117B (A5.1B) 128k — $0.14 20
— deepseek-r1 ● — deepseek-ai 671B (A37B) 160k — $2.50 2
— deepseek-r1-0528 ● — deepseek-ai 671B (A37B) 160k — $2.15 4
— deepseek-v3.1 ● — deepseek-ai 671B (A37B) 160k — $0.79 8
— deepseek-v3.1-terminus ● — deepseek-ai 671B (A37B) 160k — $0.95 5
— deepseek-v4-flash ● — deepseek-ai 158B 1024k — $0.18 16
— deepseek-v4-pro ● — deepseek-ai 862B 1024k — $0.87 16
— gemma-3-12b-it ● — google 12B 128k — $0.15 1
— gemma-3-27b-it ● — google 27B 128k — $0.16 5
— gemma-4-12b-it ● — google 12B — — — —
— gemma-4-26b-a4b-it ● — google 26.5B (A4B) 256k — $0.30 10
— gemma-4-31b-it ● — google 32.7B 256k — $0.35 13
— glm-4.5-air ● — zai-org 106B (A12B) 128k — $0.85 3
— glm-4.6v ● — zai-org 107.7B 128k — $0.90 2
— glm-4.7 ● — zai-org 358B 198k — $1.75 9
— glm-4.7-flash ● — zai-org 31.2B 198k — $0.40 4
— glm-5 ● — zai-org 754B 198k — $1.92 14
— glm-5.1 ● — zai-org 754B 198k 1472 $3.04 19
— glm-5.2 ● — zai-org 753B 1024k 1469 $3.00 28
— gpt-oss-20b ● — openai 21B (A3.6B) 128k — $0.13 13
— kimi-k2.5 ● — moonshotai 1059B (A32B) 256k — $1.90 11
— kimi-k2.6 ● — moonshotai 1059B (A32B) 256k — $3.20 21
— kimi-k2.7-code ● — moonshotai 1059B (A32B) 256k — $3.15 13
— leanstral-1.5-119b-a6b ● — mistralai 119B (A6B) — — — —
— llama-3.1-405b-instruct ● — meta-llama 405B — — — —
— llama-3.3-70b-instruct ● — meta-llama 70.6B 128k — $0.32 12
— llama-4-maverick ● — meta-llama 400B (A17B) 1024k — $0.60 5
— llama-4-scout ● — meta-llama 109B (A17B) 10000k — $0.30 4
— longcat-2.0 ● — meituan-longcat 1776B — — — —
— magistral-small-2506 ● — mistralai 24B — — — —
— mimo-v2.5-pro ● — xiaomi 1023B 1024k 1466 $0.87 5
— minimax-m1 ● — minimax 456B (A45.9B) 1000k — $2.20 2
— minimax-m2.1 ● — minimax 229B (A10B) 200k — $1.20 3
— minimax-m2.5 ● — minimax 229B (A10B) 200k — $0.48 17
— minimax-m2.7 ● — minimax 229B (A10B) 200k — $0.72 14
— minimax-m3 ● — minimax 427B 1024k — $1.20 7
— mistral-large-2411 ● — mistralai 123B — — — —
— mistral-small-3.2-24b ● — mistralai 24B 125k — $0.20 4
— olmo-2-32b-instruct ● — allenai 32B — — — —
— olmo-3-32b ● — allenai 32.2B — — — —
— ornith-1.0-35b ● — deepreinforce-ai 35B — — — —
— ornith-1.0-397b ● — deepreinforce-ai 397B — — — —
— ornith-1.0-9b ● — deepreinforce-ai 9B — — — —
— qwen-agentworld-35b-a3b ● — qwen 34.7B (A3.3B) — — — —
— qwen2.5-72b-instruct ● — qwen 72.7B 128k — $0.40 2
— qwen2.5-vl-72b-instruct ● — qwen 73.4B 128k — $1.00 1
— qwen3-235b-a22b ● — qwen 235B (A22B) 128k — $1.82 1
— qwen3-30b-a3b ● — qwen 30.5B (A3.3B) 128k — $0.50 3
— qwen3-32b ● — qwen 32.8B 128k — $0.28 5
— qwen3-coder-next ● — qwen 79.7B 256k — $0.80 5
— qwen3-next-80b-a3b-thinking ● — qwen 81.3B (A3B) 256k — $0.78 2
— qwen3-vl-235b-a22b-instruct ● — qwen 235.7B (A22B) 256k — $0.88 5
— qwen3-vl-235b-a22b-thinking ● — qwen 235.7B (A22B) 128k — $2.60 2
— qwen3-vl-30b-a3b-instruct ● — qwen 30.5B (A3B) 256k — $0.52 5
— qwen3-vl-30b-a3b-thinking ● — qwen 30.5B (A3B) 128k — $1.00 2
— qwen3-vl-32b-instruct ● — qwen 33.4B 256k — $0.42 1
— qwen3-vl-4b-instruct ● — qwen 4.4B — — — —
— qwen3-vl-8b-instruct ● — qwen 8.8B 250k — $0.46 2
— qwen3-vl-8b-thinking ● — qwen 8.8B 250k — $1.36 1
— qwen3.5-122b-a10b ● — qwen 125B (A10B) 256k — $2.08 4
— qwen3.5-27b ● — qwen 27.8B 256k — $1.56 6
— qwen3.5-35b-a3b ● — qwen 36B (A3B) 256k — $1.00 9
— qwen3.5-397b-a17b ● — qwen 403B (A17B) 250k — $2.34 12
— qwen3.5-9b ● — qwen 9.7B 256k — $0.15 4
— qwen3.6-27b ● — qwen 27.8B 256k — $2.00 9
— qwen3.6-35b-a3b ● — qwen 36B (A3.3B) 256k — $0.97 5
— qwq-32b ● — qwen 32.8B — — — —