Noometry

Model comparison

GPT-4 Turbo vs o1-mini

o1-mini is the stronger model overall, scoring 34.0 to 30.5 on the Noometry Index.

Last verified . 26 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

o1-mini OpenAI

34.0

Rank #235 Confirmed

Summary

  • They share 26 benchmarks with published results for both. GPT-4 Turbo scores higher in 1 category and o1-mini in 7 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where o1-mini leads 35.4 to 9.0.
  • The biggest single-benchmark swing is MATH Level 5: 46.7% for GPT-4 Turbo and 89.2% for o1-mini.

Side by side

GPT-4 Turboo1-mini
ProviderOpenAIOpenAI
Noometry Index30.534.0
Released2023-11-062024-09-12
WeightsProprietaryProprietary
Context window128K—
Max output4K—
Input $ / M tokens$10—
Output $ / M tokens$30—
Results tracked3639

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

Category by category

Coding o1-mini leads

GPT-4 Turbo: 33.8 (#249), o1-mini: 35.5 (#224)

BenchmarkGPT-4 Turboo1-mini
WeirdML18%36.3%
LMArena Coding12681362
HumanEval+86.6%89%
MBPP+73.3%78.8%
Aider Polyglot—32.9%
BigCodeBench Instruct48.2%—
LiveBench Coding—48%
BigCodeBench Complete58.2%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, o1-mini: 24.6 (#118)

BenchmarkGPT-4 Turboo1-mini
Cybench—10%
METR Time Horizons36.7%—

Reasoning GPT-4 Turbo leads

GPT-4 Turbo: 15.3 (#317), o1-mini: 8.8 (#346)

BenchmarkGPT-4 Turboo1-mini
SimpleBench25.1%18.1%
LMArena Hard Prompts12511333
Epoch Capabilities Index127.25135.82
ARC-AGI-2—0.8%
ARC-AGI-1—14%
Chess Puzzles6%—
LiveBench Reasoning—72.3%
DTBench61.6%—
LiveBench Data Analysis—57.9%
LMCA9.8%—
ForecastBench59.4—
LiveBench—57.8%

Math o1-mini leads

GPT-4 Turbo: 9.0 (#322), o1-mini: 35.4 (#186)

BenchmarkGPT-4 Turboo1-mini
OTIS Mock AIME 2024-20256.7%46.9%
LMArena Math12721358
MATH Level 546.7%89.2%
FrontierMath (Tiers 1-3)0.7%—
LiveBench Math—62%
FrontierMath (Feb 2025 set)—1.7%

Knowledge o1-mini leads

GPT-4 Turbo: 24.3 (#268), o1-mini: 34.9 (#192)

BenchmarkGPT-4 Turboo1-mini
GPQA Diamond46.6%62.4%
Confabulations28.4%18.6%
LMArena Expert12231316
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), o1-mini: —

BenchmarkGPT-4 Turboo1-mini
LMArena Vision1090—

Multilingual o1-mini leads

GPT-4 Turbo: 40.5 (#216), o1-mini: 43.6 (#182)

BenchmarkGPT-4 Turboo1-mini
LMArena Non-English12451289
LMArena Chinese12421314
LMArena French12761293
LMArena German12591278
LMArena Japanese11941245
LMArena Korean11871223
LMArena Russian12591283
LMArena Spanish12601303

Instruction Following Too close to call

GPT-4 Turbo: 65.8 (#216), o1-mini: 66.7 (#206)

BenchmarkGPT-4 Turboo1-mini
LMArena Instruction Following12491304
LiveBench Instruction Following—65.4%

Long Context o1-mini leads

GPT-4 Turbo: 38.0 (#206), o1-mini: 40.1 (#161)

BenchmarkGPT-4 Turboo1-mini
LMArena Longer Query12541320

Writing & Preference Too close to call

GPT-4 Turbo: 47.7 (#206), o1-mini: 48.4 (#202)

BenchmarkGPT-4 Turboo1-mini
LMArena Text12721317
LMArena Creative Writing12691244
LMArena Multi-Turn12671314
Short-Story Creative Writing—64.9%
LiveBench Language—40.9%

Frequently asked questions

Is GPT-4 Turbo better than o1-mini?

o1-mini is the stronger model overall, scoring 34.0 to 30.5 on the Noometry Index.

Is GPT-4 Turbo or o1-mini better for coding?

o1-mini scores higher on coding benchmarks: 35.5 versus 33.8 in the Noometry coding category.

How many benchmarks do GPT-4 Turbo and o1-mini share?

26 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and o1-mini has 39.

Related comparisons

Go deeper