skynet · general
SKYNET

ollama-cl/qwen3.5:397b

Qwen3.5 397B (ollama-cluster, untested)

⚖ COMPARE MODELS
VALS INDEX
44.4% +/- 44.0
Accuracy
VALS INDEX
48.7s
Latency (median)
$VALS INDEX
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS11
RECORDED TRIALS142
CUSTOM PASS36%

Industry benchmarks

Accuracyattempts · responded
GPQA_DIAMOND GPQA Diamond
13.3%
60 attempts · 60 responded
IFEVAL IFEval
75.6%
30 attempts · 30 responded
Industry benchmark Bars = accuracy %, black cap = that score

Custom 9-task suite

Mean /5n=trials
CUSTOM agentic_tool_use
5.00
3 trials
CUSTOM reasoning_multistep
5.00
8 trials
CUSTOM summarize
3.00
8 trials
CUSTOM json_strict
1.88
8 trials
CUSTOM code_gen_long -
1.12
8 trials
CUSTOM creative_write -
0.33
3 trials
CUSTOM code_debug -
0.25
8 trials
CUSTOM agentic_prompt -
0.00
3 trials
CUSTOM refactor_existing_code -
0.00
3 trials
Custom suite · scored 0–5 by consensus (m3 + Fable-5) ★ = task scored a 5 at least once · sorted by mean score

Cross-judge validation

m3 vs Fable-5 Δ

No judge bias detected on this model — m3 and Fable-5 agree across all tasks.

Per-task distribution

Score

All trials on this page were run through the harness. Industry suites use deterministic family-specific reference graders (no LLM judge). The custom suite is graded by consensus of minimax-m3 + claude-fable-5. See /industry/ for the full benchmark suite.