codex-cli · reasoning
CODEX-CLI

codex-gpt-5.6-sol

OpenAI GPT-5.6 Sol (Codex $200 plan) — flagship agentic coding

⚖ COMPARE MODELS
VALS INDEX
88.7% +/- 7.6
Accuracy
VALS INDEX
11.9s
Latency (median)
$VALS INDEX
$7.2342
Cost / Test (1P-est)
SCORE STATUSscored
TEST SETS13
RECORDED TRIALS270
CUSTOM PASS80%

Industry benchmarks

Accuracyattempts · responded
GPQA_DIAMOND GPQA Diamond
93.3%
30 attempts · 29 responded
HUMANEVAL_PLUS HumanEval+
92.0%
50 attempts · 50 responded
IFEVAL IFEval
77.3%
50 attempts · 50 responded
MMLU_PRO MMLU-Pro
92.0%
50 attempts · 50 responded
Industry benchmark Bars = accuracy %, black cap = that score

Custom 9-task suite

Mean /5n=trials
CUSTOM agentic_prompt
5.00
10 trials
CUSTOM code_gen_long
5.00
10 trials
CUSTOM json_strict
5.00
10 trials
CUSTOM reasoning_multistep
5.00
10 trials
CUSTOM agentic_tool_use
4.80
10 trials
CUSTOM code_debug
4.70
10 trials
CUSTOM summarize
4.10
10 trials
CUSTOM refactor_existing_code -
2.30
10 trials
CUSTOM creative_write
1.50
10 trials
Custom suite · scored 0–5 by consensus (m3 + Fable-5) ★ = task scored a 5 at least once · sorted by mean score

Cross-judge validation

m3 vs Fable-5 Δ

No judge bias detected on this model — m3 and Fable-5 agree across all tasks.

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.