Noometry

Model comparison

Gemini 2.5 Deep Think vs GPT-5.5

GPT-5.5 has enough public results to be ranked (#8); Gemini 2.5 Deep Think does not yet, so treat this comparison as directional.

Last verified . 2 shared benchmarks.

Gemini 2.5 Deep Think Google

—

Unranked

GPT-5.5 OpenAI

63.4

Rank #8 Confirmed

Summary

  • They share 2 benchmarks with published results for both.

Side by side

Gemini 2.5 Deep ThinkGPT-5.5
ProviderGoogleOpenAI
Noometry Index—63.4
Released2025-08-012026-04-23
WeightsProprietaryProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$5
Output $ / M tokens—$30
Results tracked271

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Gemini 2.5 Deep Think: —, GPT-5.5: 58.3 (#13)

BenchmarkGemini 2.5 Deep ThinkGPT-5.5
SWE-bench Verified—80.6%
DeepSWE—67%
FrontierCode—43%
LMArena WebDev—1512
SciCode—56.1%
GSO—40.2%
WeirdML—84.9%
LMArena Coding—1494
MirrorCode—10%
ALE-Bench—1,943

Agentic & Tool Use Not comparable

Gemini 2.5 Deep Think: —, GPT-5.5: 50.7 (#6)

BenchmarkGemini 2.5 Deep ThinkGPT-5.5
Terminal-Bench—84.7%
APEX-Agents—55.1%
OSWorld 2.0—13%
Remote Labor Index—6.3%
τ²-bench Banking—44.6%
DeepResearch Bench—54%
PostTrainBench—27.2%
ExploitBench—47.4%
GBAEval—53.2%
GDP.pdf—26%
LMArena Search—1242
Vending-Bench 2—7,524

Reasoning Not comparable

Gemini 2.5 Deep Think: —, GPT-5.5: 72.7 (#8)

BenchmarkGemini 2.5 Deep ThinkGPT-5.5
ARC-AGI-2—85%
SimpleBench—69%
Kagi LLM Benchmark—88.8%
NYT Connections (extended)—96.2%
ARC-AGI-1—95%
CritPt—27.1%
Chess Puzzles—54%
EBR-Bench—34.3%
LMArena Hard Prompts—1489
Mystery Game Puzzles—56%
DTBench—96%
LMCA—54.3%
Surface Evolver Bench—88.1%
Bench to the Future 3—0.14
Epoch Capabilities Index—159.25
ForecastBench—60.6

Math Not comparable

Gemini 2.5 Deep Think: —, GPT-5.5: 81.5 (#9)

BenchmarkGemini 2.5 Deep ThinkGPT-5.5
FrontierMath (Feb 2025 set)29%51.7%
FrontierMath Tier 4 (v1)10.4%35.4%
FrontierMath (Tiers 1-3)—85.3%
FrontierMath Tier 4—72.5%
MathArena Final-Answer Competitions—94.3%
OTIS Mock AIME 2024-2025—100%
ProofBench—50%
LMArena Math—1486
FrontierMath Erdős—0%

Knowledge Not comparable

Gemini 2.5 Deep Think: —, GPT-5.5: 64.4 (#14)

BenchmarkGemini 2.5 Deep ThinkGPT-5.5
GPQA Diamond—94%
SimpleQA Verified—63%
Vectara Hallucination Rate—9.3%
LMArena Expert—1508

Multimodal Not comparable

Gemini 2.5 Deep Think: —, GPT-5.5: 47.1 (#11)

BenchmarkGemini 2.5 Deep ThinkGPT-5.5
LMArena Vision—1297
Blueprint-Bench 2—36.2%
Furniture Assembly—44.2%
LMArena Document—1486

Multilingual Not comparable

Gemini 2.5 Deep Think: —, GPT-5.5: 56.5 (#19)

BenchmarkGemini 2.5 Deep ThinkGPT-5.5
LMArena Non-English—1467
LMArena Chinese—1535
LMArena French—1486
LMArena German—1478
LMArena Japanese—1498
LMArena Korean—1461
LMArena Russian—1473
LMArena Spanish—1469

Instruction Following Not comparable

Gemini 2.5 Deep Think: —, GPT-5.5: 77.7 (#18)

BenchmarkGemini 2.5 Deep ThinkGPT-5.5
LMArena Instruction Following—1479

Long Context Not comparable

Gemini 2.5 Deep Think: —, GPT-5.5: 48.3 (#12)

BenchmarkGemini 2.5 Deep ThinkGPT-5.5
CL-bench Life—22.2%
LMArena Longer Query—1484

Writing & Preference Not comparable

Gemini 2.5 Deep Think: —, GPT-5.5: 72.8 (#13)

BenchmarkGemini 2.5 Deep ThinkGPT-5.5
LMArena Text—1471
LMArena Creative Writing—1455
EQ-Bench Creative Writing—1844
EQ-Bench 4—1315
LMArena Multi-Turn—1477

Frequently asked questions

Is Gemini 2.5 Deep Think better than GPT-5.5?

GPT-5.5 has enough public results to be ranked (#8); Gemini 2.5 Deep Think does not yet, so treat this comparison as directional.

How many benchmarks do Gemini 2.5 Deep Think and GPT-5.5 share?

2 benchmarks have published results for both models. Gemini 2.5 Deep Think has 2 scored results on Noometry and GPT-5.5 has 71.

Related comparisons

Go deeper