AD-100 run scores

Final score = challenge weight × partial score, summed over 78 challenges (max 744.00). Click a header to sort. Trajectories →

#RunPassedFailedErrorFinal scoreAvg tokens/task% of max
1 qwen3.8_27b_Q4
unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL
56220 394.68 / 744.00 52.5k
53.0%
2 Qwen3.8-Flash-Next-UD-IQ3_XXS
unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
51270 378.85 / 744.00 46.0k
50.9%
3 Qwen3.8-Flash-Next-GSQ-RCO-Coder-IQ1_M
ISTA-DASLab/Qwen3.8-Flash-Next-Coder-GSQ-RCO-IQ1_M
49290 347.50 / 744.00 49.6k
46.7%
4 muse_glimmer_30b_q4
unsloth/Muse-Glimmer-30B-GGUF:UD-Q4_K_XL
46320 344.05 / 744.00 34.8k
46.2%
5 ornith1.5_35b_q4
bartowski/Ornith-1.5-35B-A3B-GGUF:Q4_K_M
41370 337.72 / 744.00 62.5k
45.4%
6 Flint-Q4
unsloth/flint-GGUF:UD-Q4_K_XL
49290 329.02 / 744.00 70.6k
44.2%
7 nemotron_35_bolt
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF
47310 307.88 / 744.00 65.7k
41.4%
8 gemma-4-31B-it-UD-Q4_K_XL
unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL
43350 307.40 / 744.00 21.8k
41.3%
9 Qwen3.8-27B-UD-Q2_K_XL (UD v3.1)
unsloth/Qwen3.8-27B-GGUF:UD-Q2_K_XL Q8_0 KV cache
46320 306.82 / 744.00 46.5k
41.2%
10 Qwen-AgentWorld-35B-A3B-UD-Q4_K_XL
unsloth/Qwen-AgentWorld-35B-A3B-GGUF:UD-Q4_K_XL
33450 293.23 / 744.00 43.3k
39.4%
11 Qwen3.8-27B-UD-Q2_K_XL (old UDv3)
unsloth/Qwen3.8-27B-GGUF:UD-Q2_K_XL Q8_0 KV cache
49290 291.57 / 744.00 61.7k
39.2%
12 qwen3.6_35b_q4
unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q4_K_XL
36420 274.25 / 744.00 69.5k
36.9%
13 gemma26b_Q6
unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q6_K_XL
37410 265.77 / 744.00 51.3k
35.7%
14 XYZAILab_XYZ-Aquila-mini-Q5_K_M
bartowski/XYZAILab_XYZ-Aquila-mini-GGUF:Q5_K_M
28500 213.28 / 744.00 93.5k
28.7%
15 MiniCPM-V-4.7-35B-A3B-Q4
openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q4_K_M
28500 203.45 / 744.00 20.5k
27.4%
16 gpt-oss-20b-F16
unsloth/gpt-oss-20b-GGUF:F16
29490 188.97 / 744.00 13.2k
25.4%
17 Nemotron-3.5-Lightning-30B-A3B-UD-Q4_K_XL
unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL
25530 156.87 / 744.00 98.0k
21.1%
18 Apex-35B-V1.0-Q4
Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M
22560 142.37 / 744.00 81.6k
19.1%