★VALS INDEX
67.3%
+/- 23.8
Accuracy
⏱VALS INDEX
14.5s
Latency (median)
$VALS INDEX
—
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS12
RECORDED TRIALS144
CUSTOM PASS69%
Industry benchmarks
Accuracyattempts · responded
GPQA_DIAMOND
GPQA Diamond
40.0%
30 attempts · 30 responded
HUMANEVAL_PLUS
HumanEval+
84.0%
50 attempts · 49 responded
IFEVAL
IFEval
77.8%
12 attempts · 12 responded
Custom 9-task suite
Mean /5n=trials
CUSTOM
json_strict
★
5.00
8 trials
CUSTOM
reasoning_multistep
★
5.00
8 trials
CUSTOM
summarize
★
4.88
8 trials
CUSTOM
agentic_tool_use
★
4.33
3 trials
CUSTOM
code_gen_long
★
4.00
8 trials
CUSTOM
refactor_existing_code
-
3.33
3 trials
CUSTOM
creative_write
★
2.33
3 trials
CUSTOM
code_debug
-
2.25
8 trials
CUSTOM
agentic_prompt
★
1.67
3 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.