skynet · general
SKYNET

mistral/mistral-medium

Mistral Medium

⚖ COMPARE MODELS
VALS INDEX
66.4% +/- 25.6
Accuracy
VALS INDEX
3.4s
Latency (median)
$VALS INDEX
$0.3179
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS13
RECORDED TRIALS573
CUSTOM PASS62%

Industry benchmarks

Accuracyattempts · responded
GPQA_DIAMOND GPQA Diamond
58.5%
130 attempts · 129 responded
HUMANEVAL_PLUS HumanEval+
97.5%
40 attempts · 40 responded
IFEVAL IFEval
73.1%
130 attempts · 130 responded
MMLU_PRO MMLU-Pro
36.5%
200 attempts · 200 responded
Industry benchmark Bars = accuracy %, black cap = that score

Custom 9-task suite

Mean /5n=trials
CUSTOM json_strict
5.00
6 trials
CUSTOM reasoning_multistep
5.00
6 trials
CUSTOM code_gen_long
4.82
11 trials
CUSTOM summarize
4.73
11 trials
CUSTOM agentic_tool_use
4.67
3 trials
CUSTOM refactor_existing_code -
3.67
3 trials
CUSTOM agentic_prompt
3.64
11 trials
CUSTOM code_debug
3.09
11 trials
CUSTOM creative_write -
0.00
11 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.