claude-cli · general
CLAUDE-CLI

claude-sonnet

Anthropic Sonnet (subscription)

⚖ COMPARE MODELS
VALS INDEX
70.6% +/- 23.8
Accuracy
VALS INDEX
9.6s
Latency (median)
$VALS INDEX
$2.9467
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS12
RECORDED TRIALS1164
CUSTOM PASS83%

Industry benchmarks

Accuracyattempts · responded
GPQA_DIAMOND GPQA Diamond
90.0%
30 attempts · 30 responded
HUMANEVAL_PLUS HumanEval+
44.0%
100 attempts · 50 responded
IFEVAL IFEval
77.8%
30 attempts · 30 responded
Industry benchmark Bars = accuracy %, black cap = that score

Custom 9-task suite

Mean /5n=trials
CUSTOM json_strict
5.00
100 trials
CUSTOM reasoning_multistep
5.00
100 trials
CUSTOM agentic_prompt
4.92
120 trials
CUSTOM summarize
4.80
120 trials
CUSTOM code_gen_long
4.39
120 trials
CUSTOM agentic_tool_use
4.30
100 trials
CUSTOM refactor_existing_code
4.10
115 trials
CUSTOM code_debug
3.83
120 trials
CUSTOM creative_write
1.34
110 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.