skynet · reasoning
SKYNET

ollama-cl/deepseek-v4-pro

DeepSeek v4 pro via ollama-cluster

⚖ COMPARE MODELS
VALS INDEX
40.8% +/- 13.6
Accuracy
VALS INDEX
16.4s
Latency (median)
$VALS INDEX
$0.1417
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS11
RECORDED TRIALS787
CUSTOM PASS61%

Industry benchmarks

Accuracyattempts · responded
GPQA_DIAMOND GPQA Diamond
29.0%
210 attempts · 110 responded
HUMANEVAL_PLUS HumanEval+
55.0%
40 attempts · 24 responded
IFEVAL IFEval
49.7%
190 attempts · 119 responded
MMLU_PRO MMLU-Pro
29.3%
273 attempts · 165 responded
Industry benchmark Bars = accuracy %, black cap = that score

Custom 9-task suite

Mean /5n=trials
CUSTOM code_gen_long
5.00
12 trials
CUSTOM json_strict
5.00
7 trials
CUSTOM reasoning_multistep
5.00
7 trials
CUSTOM summarize
4.58
12 trials
CUSTOM agentic_prompt
3.33
12 trials
CUSTOM code_debug -
2.75
12 trials
CUSTOM creative_write -
0.33
12 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.