GPT-5.5 High

Released2026-04-23
Price per 1M$5.00 in · $30.00 out
Overall score59.5 · rank 108
Context window1,050,000 tokens
ProviderOpenAI
WeightsProprietary
ConfigurationHigh

Scores

DimensionScoreRankBenchmarks
Overall: Balanced 59.5 108 15
Overall: Coding 58.0 141 12
Overall: Reasoning 64.1 51 6
Overall: Agentic work 60.2 95 11
Overall: Frontend 53.2 177 5
Coding 58.4 121 3
Agents 60.0 73 2
Reasoning 64.1 59 6
Frontend 49.5 123 1
General 58.6 80 2
Multimodal 60.2 34 1
Value vs price+2.4180

Evidence

Coding 58.4 ±3.1

BenchmarkResultSourceDate
MirrorCode 10.0% Epoch AI 2026-08-10
DeepSWE 64.4% Epoch AI 2026-11-11
SciCode 56.1% Epoch AI 2026-11-11

Agents 60.0 ±3.0

BenchmarkResultSourceDate
Terminal-Bench 2.1 (Vals run) 76.4% Vals AI 2026-10-01
DeepResearch Bench 54.0% Epoch AI 2026-11-11

Reasoning 64.1 ±1.8

BenchmarkResultSourceDate
Extended NYT Connections 95.2% Lech Mazur 2026-11-10
ARC-AGI-2 83.3% Epoch AI 2026-11-11
ARC-AGI-2 (ARC Prize verified) 83.3% ARC Prize 2026-11-11
CritPt 25.4% Epoch AI 2026-11-11
ARC-AGI-1 (ARC Prize verified) 94.5% ARC Prize 2026-11-11
ARC-AGI-1 94.5% Epoch AI 2026-11-11
ARC-AGI-3 0.4% ARC Prize 2026-11-11
Mystery Game Puzzles 52.0% Epoch AI 2026-07-27

Frontend 49.5 ±3.0

BenchmarkResultSourceDate
LMArena WebDev 1,487 LMArena 2026-11-10

General 58.6 ±2.6

BenchmarkResultSourceDate
LLM Debate Benchmark 1,520 Lech Mazur 2026-10-26
LMArena Text 1,481 LMArena 2026-11-09

Multimodal 60.2 ±4.1

BenchmarkResultSourceDate
LMArena Vision 1,283 LMArena 2026-11-09

Names matched to this model

gpt-5-5-high

Compare GPT-5.5 High with other models