Noometry

Model comparison

Gemini 3.8 Flash vs GPT-5 Pro

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 46.4 on the Noometry Index.

Last verified . 7 shared benchmarks.

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

GPT-5 Pro OpenAI

46.4

Rank #64 Confirmed

Summary

  • They share 7 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 4 categories and GPT-5 Pro in 0 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 38.9.
  • The biggest single-benchmark swing is ARC-AGI-2: 89.2% for Gemini 3.8 Flash and 18.3% for GPT-5 Pro.
  • Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
  • Gemini 3.8 Flash accepts more context: 1.05M tokens versus 400K.

Side by side

Gemini 3.8 FlashGPT-5 Pro
ProviderGoogleOpenAI
Noometry Index61.846.4
Released2026-09-022025-10-06
WeightsProprietaryProprietary
Context window1.05M400K
Max output66K272K
Input $ / M tokens$0.75$15
Output $ / M tokens$3.75$120
Results tracked5012

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

Category by category

Coding Gemini 3.8 Flash leads

Gemini 3.8 Flash: 59.2 (#15), GPT-5 Pro: 44.0 (#80)

BenchmarkGemini 3.8 FlashGPT-5 Pro
WeirdML84.8%60.4%
DeepSWE73.8%—
FrontierCode41.2%—
CursorBench39.6%—
LMArena WebDev1584—
FrontierSWE19.6%—
SciCode56.6%—
LMArena Coding1510—
ALE-Bench1,270—
AlgoTune—1.31

Agentic & Tool Use Not comparable

Gemini 3.8 Flash: 41.8 (#21), GPT-5 Pro: —

BenchmarkGemini 3.8 FlashGPT-5 Pro
APEX-Agents64.3%—
Remote Labor Index5.8%—
GDP.pdf23.4%—
Vending-Bench 25,094—

Reasoning Gemini 3.8 Flash leads

Gemini 3.8 Flash: 76.9 (#5), GPT-5 Pro: 38.9 (#62)

BenchmarkGemini 3.8 FlashGPT-5 Pro
ARC-AGI-289.2%18.3%
ARC-AGI-198.5%70.2%
Epoch Capabilities Index156.71150.28
SimpleBench—61.6%
Kagi LLM Benchmark—76.8%
NYT Connections (extended)97.4%—
CritPt18.3%—
Chess Puzzles61%—
EnigmaEval—18.8%
LMArena Hard Prompts1508—
Mystery Game Puzzles47%—
DTBench95.7%—
LMCA52.9%—
Surface Evolver Bench76.9%—

Math Gemini 3.8 Flash leads

Gemini 3.8 Flash: 65.3 (#28), GPT-5 Pro: 48.5 (#63)

BenchmarkGemini 3.8 FlashGPT-5 Pro
FrontierMath (Tiers 1-3)68.4%55.8%
FrontierMath Tier 422%19.5%
OTIS Mock AIME 2024-202598.9%—
ProofBench48%—
LMArena Math1528—
FrontierMath Tier 4 (v1)—14.6%

Knowledge Gemini 3.8 Flash leads

Gemini 3.8 Flash: 74.8 (#2), GPT-5 Pro: 56.7 (#42)

BenchmarkGemini 3.8 FlashGPT-5 Pro
Humanity's Last Exam44.5%31.6%
GPQA Diamond95.4%—
SimpleQA Verified69.7%—
LMArena Expert1524—

Multimodal Not comparable

Gemini 3.8 Flash: 40.7 (#45), GPT-5 Pro: —

BenchmarkGemini 3.8 FlashGPT-5 Pro
LMArena Vision1314—
Blueprint-Bench 238.6%—
Furniture Assembly31.7%—

Multilingual Not comparable

Gemini 3.8 Flash: 58.0 (#5), GPT-5 Pro: —

BenchmarkGemini 3.8 FlashGPT-5 Pro
LMArena Non-English1491—
LMArena Chinese1554—
LMArena French1498—
LMArena German1493—
LMArena Japanese1502—
LMArena Korean1459—
LMArena Russian1515—
LMArena Spanish1485—

Instruction Following Not comparable

Gemini 3.8 Flash: 78.0 (#13), GPT-5 Pro: —

BenchmarkGemini 3.8 FlashGPT-5 Pro
LMArena Instruction Following1490—

Long Context Not comparable

Gemini 3.8 Flash: 46.3 (#24), GPT-5 Pro: —

BenchmarkGemini 3.8 FlashGPT-5 Pro
LMArena Longer Query1508—

Writing & Preference Not comparable

Gemini 3.8 Flash: 72.2 (#15), GPT-5 Pro: —

BenchmarkGemini 3.8 FlashGPT-5 Pro
LMArena Text1499—
LMArena Creative Writing1492—
EQ-Bench Creative Writing1748—
LMArena Multi-Turn1501—

Frequently asked questions

Is Gemini 3.8 Flash better than GPT-5 Pro?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 46.4 on the Noometry Index.

Which is cheaper, Gemini 3.8 Flash or GPT-5 Pro?

Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-5 Pro lists at $15 and $120.

Is Gemini 3.8 Flash or GPT-5 Pro better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 44.0 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 400K.

How many benchmarks do Gemini 3.8 Flash and GPT-5 Pro share?

7 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and GPT-5 Pro has 12.

Related comparisons

Go deeper