claude-cli · reasoning
CLAUDE-CLI

claude-opus

Anthropic Opus 4.8 alias (subscription)

⚖ COMPARE MODELS
VALS INDEX
69.7% +/- 25.3
Accuracy
VALS INDEX
14.0s
Latency (median)
$VALS INDEX
$13.3107
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS12
RECORDED TRIALS1051
CUSTOM PASS78%

Industry benchmarks

Accuracyattempts · responded
GPQA_DIAMOND GPQA Diamond
93.3%
30 attempts · 30 responded
HUMANEVAL_PLUS HumanEval+
43.0%
100 attempts · 50 responded
IFEVAL IFEval
72.8%
30 attempts · 30 responded
Industry benchmark Bars = accuracy %, black cap = that score

Custom 9-task suite

Mean /5n=trials
CUSTOM json_strict
5.00
95 trials
CUSTOM reasoning_multistep
5.00
80 trials
CUSTOM agentic_prompt
4.88
101 trials
CUSTOM summarize
4.67
111 trials
CUSTOM agentic_tool_use
4.59
75 trials
CUSTOM code_gen_long
4.38
120 trials
CUSTOM refactor_existing_code
3.69
85 trials
CUSTOM code_debug
3.16
120 trials
CUSTOM creative_write
2.01
105 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.