skynet · general
SKYNET

ollama-cl/gpt-oss:120b

OpenAI gpt-oss 120B (ollama-cluster, untested)

⚖ COMPARE MODELS
VALS INDEX
43.4% +/- 11.9
Accuracy
VALS INDEX
10.5s
Latency (median)
$VALS INDEX
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS11
RECORDED TRIALS199
CUSTOM PASS67%

Industry benchmarks

Accuracyattempts · responded
GPQA_DIAMOND GPQA Diamond
51.8%
110 attempts · 105 responded
MMLU_PRO MMLU-Pro
35.0%
80 attempts · 66 responded
Industry benchmark Bars = accuracy %, black cap = that score

Custom 9-task suite

Mean /5n=trials
CUSTOM agentic_tool_use
5.00
1 trials
CUSTOM code_gen_long
5.00
1 trials
CUSTOM json_strict
5.00
1 trials
CUSTOM reasoning_multistep
5.00
1 trials
CUSTOM code_debug -
4.00
1 trials
CUSTOM summarize -
4.00
1 trials
CUSTOM agentic_prompt -
3.00
1 trials
CUSTOM refactor_existing_code -
3.00
1 trials
CUSTOM creative_write -
0.00
1 trials
Custom suite · scored 0–5 by consensus (m3 + Fable-5) ★ = task scored a 5 at least once · sorted by mean score

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.