Noometry

Model comparison

Gemini 1.0 Pro vs o1

o1 is the stronger model overall, scoring 40.9 to 27.3 on the Noometry Index.

Last verified . 23 shared benchmarks.

Gemini 1.0 Pro Google

27.3

Rank #332 Confirmed

o1 OpenAI

40.9

Rank #143 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 0 categories and o1 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where o1 leads 36.1 to 9.3.
  • The biggest single-benchmark swing is MATH Level 5: 11.2% for Gemini 1.0 Pro and 94.7% for o1.

Side by side

Gemini 1.0 Proo1
ProviderGoogleOpenAI
Noometry Index27.340.9
Released2023-12-132024-09-12
WeightsProprietaryProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$15
Output $ / M tokens—$60
Results tracked2452

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

Category by category

Coding o1 leads

Gemini 1.0 Pro: 32.2 (#275), o1: 46.1 (#70)

BenchmarkGemini 1.0 Proo1
LMArena Coding11081367
HumanEval+55.5%89%
MBPP+61.4%80.2%
Aider Polyglot—61.7%
WeirdML—47.6%
LiveBench Coding—69.7%
CadEval—56%

Agentic & Tool Use Not comparable

Gemini 1.0 Pro: —, o1: 24.6 (#117)

BenchmarkGemini 1.0 Proo1
Cybench—10%
METR Time Horizons—51.1%

Reasoning o1 leads

Gemini 1.0 Pro: 17.1 (#296), o1: 27.9 (#111)

BenchmarkGemini 1.0 Proo1
LMArena Hard Prompts11091371
DTBench45.9%74.7%
Epoch Capabilities Index117.04141.91
SimpleBench—41.7%
ARC-AGI-1—30.7%
Chess Puzzles—15%
EnigmaEval—5.7%
LiveBench Reasoning—91.6%
LiveBench Data Analysis—65.5%
LMCA—22.3%
LiveBench—75.7%

Math o1 leads

Gemini 1.0 Pro: 9.3 (#321), o1: 36.1 (#175)

BenchmarkGemini 1.0 Proo1
OTIS Mock AIME 2024-20251.1%73.3%
LMArena Math11321388
MATH Level 511.2%94.7%
FrontierMath (Tiers 1-3)—14.7%
LiveBench Math—80.3%
FrontierMath (Feb 2025 set)—9.3%

Knowledge o1 leads

Gemini 1.0 Pro: 15.6 (#291), o1: 41.5 (#110)

BenchmarkGemini 1.0 Proo1
GPQA Diamond34%76.8%
LMArena Expert10591361
Humanity's Last Exam—8%
SimpleQA Verified—41.1%
Confabulations—11.7%
MMLU70%—

Multimodal Not comparable

Gemini 1.0 Pro: —, o1: 34.2 (#93)

BenchmarkGemini 1.0 Proo1
LMArena Vision—1168
GeoBench—80%
VPCT—37%
SpatialViz-Bench—41.4%

Multilingual o1 leads

Gemini 1.0 Pro: 33.4 (#252), o1: 48.6 (#142)

BenchmarkGemini 1.0 Proo1
LMArena Non-English11381358
LMArena Chinese11241394
LMArena French11451344
LMArena German11251337
LMArena Japanese10231346
LMArena Russian11861356
LMArena Spanish11191345
LMArena Korean—1396

Instruction Following o1 leads

Gemini 1.0 Pro: 57.6 (#267), o1: 74.8 (#86)

BenchmarkGemini 1.0 Proo1
LMArena Instruction Following11141367
LiveBench Instruction Following—81.5%

Long Context o1 leads

Gemini 1.0 Pro: 34.3 (#249), o1: 50.3 (#9)

BenchmarkGemini 1.0 Proo1
LMArena Longer Query11321378
Fiction.LiveBench—83.3%

Writing & Preference o1 leads

Gemini 1.0 Pro: 36.0 (#264), o1: 55.6 (#144)

BenchmarkGemini 1.0 Proo1
LMArena Text11491366
LMArena Creative Writing11311348
LMArena Multi-Turn11391369
Short-Story Creative Writing—70.2%
LiveBench Language—65.4%

Frequently asked questions

Is Gemini 1.0 Pro better than o1?

o1 is the stronger model overall, scoring 40.9 to 27.3 on the Noometry Index.

Is Gemini 1.0 Pro or o1 better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 32.2 in the Noometry coding category.

How many benchmarks do Gemini 1.0 Pro and o1 share?

23 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and o1 has 52.

Related comparisons

Go deeper