— · general

claude-cli/claude-fable

The harness recorded 300 industry attempts, but this route returned no usable response; it is reported as not scored rather than as 0% accuracy.

⚖ COMPARE MODELS
VALS INDEX
Accuracy
VALS INDEX
Latency (median)
$VALS INDEX
Cost / Test (1P-est)
SCORE STATUSnot scored
TEST SETS3
RECORDED TRIALS300
CUSTOM PASS

Industry benchmarks

Accuracyattempts · responded
GPQA_DIAMOND GPQA Diamond
not scored
50 attempts · 0 responded
IFEVAL IFEval
not scored
110 attempts · 0 responded
MMLU_PRO MMLU-Pro
not scored
140 attempts · 0 responded
Industry benchmark Bars = accuracy %, black cap = that 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.