Noometry

Model comparison

Gemini 2.5 Pro vs GPT-6.1 Sol

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 45.0 on the Noometry Index.

Last verified . 24 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 3 categories and GPT-6.1 Sol in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 32.5.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 0% for Gemini 2.5 Pro and 100% for GPT-6.1 Sol.
  • Gemini 2.5 Pro is cheaper at $1.25 / $10 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
  • GPT-6.1 Sol accepts more context: 1.05M tokens versus 1.05M.

Side by side

Gemini 2.5 ProGPT-6.1 Sol
ProviderGoogleOpenAI
Noometry Index45.065.6
Released2025-03-252026-09-29
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K128K
Input $ / M tokens$1.25$2
Output $ / M tokens$10$10
Results tracked7834

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

Category by category

Coding GPT-6.1 Sol leads

Gemini 2.5 Pro: 42.4 (#101), GPT-6.1 Sol: 63.2 (#8)

BenchmarkGemini 2.5 ProGPT-6.1 Sol
LMArena WebDev12271755
SciCode42.8%55.8%
LMArena Coding14521487
SWE-bench Verified57.6%—
DeepSWE—75.2%
FrontierCode—50.2%
SWE-bench Verified (bash only)53.6%—
Aider Polyglot83.1%—
GSO3.9%—
WeirdML54%—
LiveBench Coding85.9%—
CadEval64%—
ALE-Bench785.52—
AlgoTune1.51—

Agentic & Tool Use GPT-6.1 Sol leads

Gemini 2.5 Pro: 29.2 (#88), GPT-6.1 Sol: 39.6 (#26)

BenchmarkGemini 2.5 ProGPT-6.1 Sol
Terminal-Bench32.6%—
APEX-Agents—60%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
BALROG43.3%—
GDP.pdf—32%
LMArena Search1142—
METR Time Horizons55.4%—
Vending-Bench 2573.64—

Reasoning GPT-6.1 Sol leads

Gemini 2.5 Pro: 28.8 (#99), GPT-6.1 Sol: 81.9 (#2)

BenchmarkGemini 2.5 ProGPT-6.1 Sol
ARC-AGI-24.9%94.2%
ARC-AGI-141%98.5%
CritPt2%31.7%
Chess Puzzles20%61%
LMArena Hard Prompts14551466
Epoch Capabilities Index145.32166.09
SimpleBench62.4%—
Kagi LLM Benchmark70.3%—
NYT Connections (extended)—95.5%
EnigmaEval5.6%—
EBR-Bench—54.3%
LiveBench Reasoning89.8%—
Mystery Game Puzzles—80%
DTBench82.4%—
LiveBench Data Analysis79.9%—
LMCA34.8%—
ForecastBench61.3—
LiveBench82.3%—

Math GPT-6.1 Sol leads

Gemini 2.5 Pro: 32.5 (#213), GPT-6.1 Sol: 93.7 (#1)

BenchmarkGemini 2.5 ProGPT-6.1 Sol
FrontierMath (Tiers 1-3)24.6%93.7%
FrontierMath Tier 40%100%
OTIS Mock AIME 2024-202584.7%100%
LMArena Math14501464
ProofBench—99%
Omni-MATH41.6%—
LiveBench Math90.2%—
MATH Level 595.9%—
FrontierMath (Feb 2025 set)14.1%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge GPT-6.1 Sol leads

Gemini 2.5 Pro: 56.0 (#46), GPT-6.1 Sol: 71.8 (#4)

BenchmarkGemini 2.5 ProGPT-6.1 Sol
GPQA Diamond85.3%95.4%
LMArena Expert14521502
Humanity's Last Exam21.6%—
SimpleQA Verified—73.9%
MMLU-Pro86.3%—
Confabulations10.6%—
Vectara Hallucination Rate7%—
GPQA (HELM)74.9%—

Multimodal GPT-6.1 Sol leads

Gemini 2.5 Pro: 45.2 (#18), GPT-6.1 Sol: 52.7 (#5)

BenchmarkGemini 2.5 ProGPT-6.1 Sol
LMArena Vision12631288
GeoBench86%—
VPCT48%—
Furniture Assembly—80%
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Too close to call

Gemini 2.5 Pro: 55.3 (#31), GPT-6.1 Sol: 54.3 (#46)

BenchmarkGemini 2.5 ProGPT-6.1 Sol
LMArena Non-English14511438
LMArena Chinese15071477
LMArena Russian14611455
LMArena French1472—
LMArena German1487—
LMArena Japanese1461—
LMArena Korean1434—
LMArena Spanish1473—

Instruction Following GPT-6.1 Sol leads

Gemini 2.5 Pro: 75.0 (#75), GPT-6.1 Sol: 77.0 (#29)

BenchmarkGemini 2.5 ProGPT-6.1 Sol
LMArena Instruction Following14371468
LiveBench Instruction Following80.6%—
IFEval84%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), GPT-6.1 Sol: 44.9 (#54)

BenchmarkGemini 2.5 ProGPT-6.1 Sol
LMArena Longer Query14491465
Fiction.LiveBench91.7%—

Writing & Preference Too close to call

Gemini 2.5 Pro: 63.7 (#62), GPT-6.1 Sol: 63.6 (#63)

BenchmarkGemini 2.5 ProGPT-6.1 Sol
LMArena Text14581447
LMArena Creative Writing14541432
LMArena Multi-Turn14531449
Short-Story Creative Writing83.8%—
EQ-Bench Creative Writing1421—
WildBench85.7%—
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than GPT-6.1 Sol?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 45.0 on the Noometry Index.

Which is cheaper, Gemini 2.5 Pro or GPT-6.1 Sol?

Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; GPT-6.1 Sol lists at $2 and $10.

Is Gemini 2.5 Pro or GPT-6.1 Sol better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

GPT-6.1 Sol does, with 1.05M tokens against 1.05M.

How many benchmarks do Gemini 2.5 Pro and GPT-6.1 Sol share?

24 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and GPT-6.1 Sol has 34.

Related comparisons

Go deeper