Benchrun Benchmark Report

Set: quick | Created: 2026-07-16T14:51:08.046049 | Models tested: 2
Models2
Avg Score72.5%
Best Modelgemma4:26b
Categories (7) & Details
ModelScorePassedTotal
gemma4:26b 80.0% 9 10
Q#QuestionScoreStatusReason
0 Complex State Tracing 0.50 PASS keyword(1/2)
1 Probability Reasoning 0.00 FAIL keyword(0/2)
2 List Compression One-Liner 1.00 PASS keyword(2/2)
3 Singleton Thread Safety 1.00 PASS keyword(2/2)
4 Raw JSON Output 1.00 PASS keyword(0/0)
5 MoE Compute Benefit 1.00 PASS keyword(2/2)
6 Instruction Injection Test 1.00 PASS keyword(1/1)
7 CAP Theorem Tradeoffs 1.00 PASS keyword(2/2)
8 GQA Inference Benefit 1.00 PASS keyword(2/2)
9 Senior Engineer Critique 0.50 PASS keyword(2/4)
qwen3.6:35b-a3b-mtp-q4_K_M 65.0% 8 10
Categories (7) & Details
Q#QuestionScoreStatusReason
0 Complex State Tracing 0.00 FAIL keyword(0/2)
1 Probability Reasoning 0.00 FAIL keyword(0/2)
2 List Compression One-Liner 1.00 PASS keyword(2/2)
3 Singleton Thread Safety 0.50 PASS keyword(1/2)
4 Raw JSON Output 1.00 PASS keyword(0/0)
5 MoE Compute Benefit 0.50 PASS keyword(1/2)
6 Instruction Injection Test 1.00 PASS keyword(1/1)
7 CAP Theorem Tradeoffs 1.00 PASS keyword(2/2)
8 GQA Inference Benefit 1.00 PASS keyword(2/2)
9 Senior Engineer Critique 0.50 PASS keyword(2/4)
Powered by Benchrun | 2026-07-16T14:51:08.046049