CLAUDE-CLI
claude-opus-5-high
Anthropic Opus 5 via Claude Max (high-effort benchmark variant; 1M API context)
★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
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
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.