Benchfolio

Leaderboard / Model

GPT-5.6 Sol

OpenAI · Closed weights · Released Jul 9, 2026 · $4 in · $20 out per 1M tokens

69Overall · rank 5

Score by job

Coding

75 · rank 8 · 3 of 5 benchmarks

BenchmarkResultVariantz
DeepSWE72.7%gpt-5.6-sol_max0.99
FrontierCode47.5%gpt-5.6-sol_unknown0.82
LMArena Coding1490 ratinggpt-5.6-sol-xhigh-0.04

Agents

64 · rank 5 · 2 of 4 benchmarks

BenchmarkResultVariantz
APEX-Agents51.4%gpt-5.6-sol_promax-0.09
OSWorld 2.027.3%gpt-5.6-sol_max1.07

Reasoning

76 · rank 9 · 3 of 4 benchmarks

BenchmarkResultVariantz
GPQA Diamond93.5%gpt-5.6-sol_max0.78
ARC-AGI-292.5%gpt-5.6-sol_max1.31
SimpleBench71.7%gpt-5.6-sol_proxhigh0.63

Math

76 · rank 6 · 5 of 5 benchmarks

BenchmarkResultVariantz
FrontierMath Tiers 1–389.1%gpt-5.6-sol_max1.46
FrontierMath Tier 482.9%gpt-5.6-sol_max1.75
OTIS Mock AIME100.0%gpt-5.6-sol_max1.09
ProofBench83.0%gpt-5.6-sol_max1.39
LMArena Math1466 ratinggpt-5.6-sol-xhigh-0.54

Writing

67 · rank 16 · 2 of 2 benchmarks

BenchmarkResultVariantz
LMArena Creative Writing1452 ratinggpt-5.6-sol-xhigh0.04
LMArena Instruction Following1477 ratinggpt-5.6-sol-xhigh0.48

Design

55 · rank 13 · 1 of 1 benchmarks

BenchmarkResultVariantz
LMArena WebDev1617 ratinggpt-5.6-sol-xhigh (codex-harness)0.59