Noometry

Model comparison

Gemini 3.5 Flash vs GPT-6.1 Sol

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 54.2 on the Noometry Index.

Last verified . 32 shared benchmarks.

Gemini 3.5 Flash Google

54.2

Rank #32 Confirmed

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Summary

  • They share 32 benchmarks with published results for both. Gemini 3.5 Flash 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 60.7.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 26.8% for Gemini 3.5 Flash and 100% for GPT-6.1 Sol.
  • Gemini 3.5 Flash is cheaper at $1.50 / $9 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 3.5 FlashGPT-6.1 Sol
ProviderGoogleOpenAI
Noometry Index54.265.6
Released2026-05-192026-09-29
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K128K
Input $ / M tokens$1.50$2
Output $ / M tokens$9$10
Results tracked5434

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

Category by category

Coding GPT-6.1 Sol leads

Gemini 3.5 Flash: 49.4 (#49), GPT-6.1 Sol: 63.2 (#8)

BenchmarkGemini 3.5 FlashGPT-6.1 Sol
DeepSWE37.4%75.2%
LMArena WebDev14991755
SciCode53.1%55.8%
LMArena Coding14921487
SWE-bench Verified79.3%—
FrontierCode—50.2%
WeirdML62.6%—
ALE-Bench911.02—

Agentic & Tool Use GPT-6.1 Sol leads

Gemini 3.5 Flash: 24.7 (#114), GPT-6.1 Sol: 39.6 (#26)

BenchmarkGemini 3.5 FlashGPT-6.1 Sol
APEX-Agents27.5%60%
GDP.pdf14%32%
GBAEval6.7%—
Vending-Bench 25,396—

Reasoning GPT-6.1 Sol leads

Gemini 3.5 Flash: 62.8 (#18), GPT-6.1 Sol: 81.9 (#2)

BenchmarkGemini 3.5 FlashGPT-6.1 Sol
ARC-AGI-272.1%94.2%
NYT Connections (extended)92.6%95.5%
ARC-AGI-192.5%98.5%
CritPt13.1%31.7%
Chess Puzzles50%61%
EBR-Bench4.8%54.3%
LMArena Hard Prompts14881466
Mystery Game Puzzles32%80%
Epoch Capabilities Index154.46166.09
SimpleBench76.7%—
EnigmaEval25.4%—
DTBench94.7%—
LMCA47.1%—
Surface Evolver Bench58.1%—
ForecastBench59—

Math GPT-6.1 Sol leads

Gemini 3.5 Flash: 60.7 (#36), GPT-6.1 Sol: 93.7 (#1)

BenchmarkGemini 3.5 FlashGPT-6.1 Sol
FrontierMath (Tiers 1-3)62.8%93.7%
FrontierMath Tier 426.8%100%
OTIS Mock AIME 2024-202595.6%100%
ProofBench31%99%
LMArena Math15041464
MathArena Final-Answer Competitions76.3%—
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge GPT-6.1 Sol leads

Gemini 3.5 Flash: 66.3 (#11), GPT-6.1 Sol: 71.8 (#4)

BenchmarkGemini 3.5 FlashGPT-6.1 Sol
GPQA Diamond92.8%95.4%
SimpleQA Verified66.2%73.9%
LMArena Expert14951502

Multimodal GPT-6.1 Sol leads

Gemini 3.5 Flash: 45.7 (#15), GPT-6.1 Sol: 52.7 (#5)

BenchmarkGemini 3.5 FlashGPT-6.1 Sol
LMArena Vision13101288
Blueprint-Bench 233.6%—
Furniture Assembly—80%
LMArena Document1463—

Multilingual Gemini 3.5 Flash leads

Gemini 3.5 Flash: 57.0 (#13), GPT-6.1 Sol: 54.3 (#46)

BenchmarkGemini 3.5 FlashGPT-6.1 Sol
LMArena Non-English14761438
LMArena Chinese15261477
LMArena Russian14931455
LMArena French1490—
LMArena German1492—
LMArena Japanese1486—
LMArena Korean1451—
LMArena Spanish1480—

Instruction Following Too close to call

Gemini 3.5 Flash: 77.0 (#30), GPT-6.1 Sol: 77.0 (#29)

BenchmarkGemini 3.5 FlashGPT-6.1 Sol
LMArena Instruction Following14671468

Long Context Too close to call

Gemini 3.5 Flash: 45.4 (#38), GPT-6.1 Sol: 44.9 (#54)

BenchmarkGemini 3.5 FlashGPT-6.1 Sol
LMArena Longer Query14821465

Writing & Preference Gemini 3.5 Flash leads

Gemini 3.5 Flash: 65.5 (#47), GPT-6.1 Sol: 63.6 (#63)

BenchmarkGemini 3.5 FlashGPT-6.1 Sol
LMArena Text14821447
LMArena Creative Writing14701432
LMArena Multi-Turn14811449
EQ-Bench 41087—

Frequently asked questions

Is Gemini 3.5 Flash better than GPT-6.1 Sol?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 54.2 on the Noometry Index.

Which is cheaper, Gemini 3.5 Flash or GPT-6.1 Sol?

Gemini 3.5 Flash is cheaper. It lists at $1.50 per million input tokens and $9 per million output tokens; GPT-6.1 Sol lists at $2 and $10.

Is Gemini 3.5 Flash or GPT-6.1 Sol better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 49.4 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 3.5 Flash and GPT-6.1 Sol share?

32 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and GPT-6.1 Sol has 34.

Related comparisons

Go deeper