skynet · reasoning
SKYNET

ollama-cl/deepseek-v4-flash

DeepSeek v4 flash (cheap tier, untested)

⚖ COMPARE MODELS
VALS INDEX
63.0% +/- 13.8
Accuracy
VALS INDEX
6.5s
Latency (median)
$VALS INDEX
$0.0092
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS11
RECORDED TRIALS124
CUSTOM PASS82%

Industry benchmarks

Accuracyattempts · responded
GPQA_DIAMOND GPQA Diamond
53.3%
30 attempts · 30 responded
IFEVAL IFEval
72.8%
60 attempts · 60 responded
Industry benchmark Bars = accuracy %, black cap = that score

Custom 9-task suite

Mean /5n=trials
CUSTOM code_gen_long
5.00
6 trials
CUSTOM json_strict
5.00
6 trials
CUSTOM summarize
4.83
6 trials
CUSTOM agentic_tool_use -
4.00
1 trials
CUSTOM code_debug
4.00
6 trials
CUSTOM reasoning_multistep
3.50
6 trials
CUSTOM agentic_prompt -
3.00
1 trials
CUSTOM refactor_existing_code -
3.00
1 trials
CUSTOM creative_write -
2.00
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.