★VALS INDEX
56.0%
+/- 22.6
Accuracy
⏱VALS INDEX
27.3s
Latency (median)
$VALS INDEX
$0.3018
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS11
RECORDED TRIALS142
CUSTOM PASS48%
Industry benchmarks
Accuracyattempts · responded
GPQA_DIAMOND
GPQA Diamond
40.0%
30 attempts · 30 responded
IFEVAL
IFEval
71.9%
60 attempts · 60 responded
Custom 9-task suite
Mean /5n=trials
CUSTOM
json_strict
★
5.00
8 trials
CUSTOM
reasoning_multistep
★
5.00
8 trials
CUSTOM
summarize
★
3.12
8 trials
CUSTOM
code_gen_long
★
2.62
8 trials
CUSTOM
code_debug
★
1.75
8 trials
CUSTOM
agentic_prompt
★
1.67
3 trials
CUSTOM
creative_write
-
0.67
3 trials
CUSTOM
refactor_existing_code
-
0.33
3 trials
CUSTOM
agentic_tool_use
-
0.00
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.