claude-cli · reasoning
CLAUDE-CLI

claude-opus-5-high

Anthropic Opus 5 via Claude Max (high-effort benchmark variant; 1M API context)

⚖ COMPARE MODELS
VALS INDEX
85.2% +/- 3.9
Accuracy
VALS INDEX
23.1s
Latency (median)
$VALS INDEX
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS11
RECORDED TRIALS450
CUSTOM PASS87%

Industry benchmarks

Accuracyattempts · responded
GPQA_DIAMOND GPQA Diamond
88.0%
100 attempts · 98 responded
HUMANEVAL_PLUS HumanEval+
82.5%
160 attempts · 160 responded
Industry benchmark Bars = accuracy %, black cap = that score

Custom 9-task suite

Mean /5n=trials
CUSTOM agentic_prompt
5.00
20 trials
CUSTOM json_strict
5.00
20 trials
CUSTOM reasoning_multistep
5.00
20 trials
CUSTOM summarize
4.95
20 trials
CUSTOM code_gen_long
4.86
29 trials
CUSTOM agentic_tool_use
4.70
20 trials
CUSTOM code_debug
4.20
20 trials
CUSTOM refactor_existing_code
3.86
21 trials
CUSTOM creative_write
2.25
20 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.