Noometry

Model comparison

GPT-4 Turbo vs MiMo-V2-Pro

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 30.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

MiMo-V2-Pro Xiaomi

43.0

Rank #103 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and MiMo-V2-Pro in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiMo-V2-Pro leads 39.5 to 9.0.
  • MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • MiMo-V2-Pro accepts more context: 1.05M tokens versus 128K.

Side by side

GPT-4 TurboMiMo-V2-Pro
ProviderOpenAIXiaomi
Noometry Index30.543.0
Released2023-11-062026-03-18
WeightsProprietaryProprietary
Context window128K1.05M
Max output4K131K
Input $ / M tokens$10$0.43
Output $ / M tokens$30$0.87
Results tracked3623

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

Category by category

Coding MiMo-V2-Pro leads

GPT-4 Turbo: 33.8 (#249), MiMo-V2-Pro: 43.8 (#83)

BenchmarkGPT-4 TurboMiMo-V2-Pro
LMArena Coding12681476
LMArena WebDev—1433
WeirdML18%—
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
ALE-Bench—785.17
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, MiMo-V2-Pro: —

BenchmarkGPT-4 TurboMiMo-V2-Pro
METR Time Horizons36.7%—

Reasoning MiMo-V2-Pro leads

GPT-4 Turbo: 15.3 (#317), MiMo-V2-Pro: 22.1 (#206)

BenchmarkGPT-4 TurboMiMo-V2-Pro
LMArena Hard Prompts12511457
SimpleBench25.1%—
NYT Connections (extended)—25.8%
Chess Puzzles6%—
Thematic Generalization—45.9%
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math MiMo-V2-Pro leads

GPT-4 Turbo: 9.0 (#322), MiMo-V2-Pro: 39.5 (#102)

BenchmarkGPT-4 TurboMiMo-V2-Pro
LMArena Math12721447
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
MATH Level 546.7%—

Knowledge MiMo-V2-Pro leads

GPT-4 Turbo: 24.3 (#268), MiMo-V2-Pro: 41.4 (#111)

BenchmarkGPT-4 TurboMiMo-V2-Pro
LMArena Expert12231478
GPQA Diamond46.6%—
Confabulations28.4%—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), MiMo-V2-Pro: —

BenchmarkGPT-4 TurboMiMo-V2-Pro
LMArena Vision1090—

Multilingual MiMo-V2-Pro leads

GPT-4 Turbo: 40.5 (#216), MiMo-V2-Pro: 52.7 (#81)

BenchmarkGPT-4 TurboMiMo-V2-Pro
LMArena Non-English12451416
LMArena Chinese12421456
LMArena French12761469
LMArena German12591417
LMArena Japanese11941366
LMArena Korean11871400
LMArena Russian12591427
LMArena Spanish12601457

Instruction Following MiMo-V2-Pro leads

GPT-4 Turbo: 65.8 (#216), MiMo-V2-Pro: 76.0 (#49)

BenchmarkGPT-4 TurboMiMo-V2-Pro
LMArena Instruction Following12491445

Long Context MiMo-V2-Pro leads

GPT-4 Turbo: 38.0 (#206), MiMo-V2-Pro: 41.5 (#138)

BenchmarkGPT-4 TurboMiMo-V2-Pro
LMArena Longer Query12541455
CL-bench—15.7%
CL-bench Life—6.9%

Writing & Preference MiMo-V2-Pro leads

GPT-4 Turbo: 47.7 (#206), MiMo-V2-Pro: 62.8 (#70)

BenchmarkGPT-4 TurboMiMo-V2-Pro
LMArena Text12721436
LMArena Creative Writing12691415
LMArena Multi-Turn12671456

Frequently asked questions

Is GPT-4 Turbo better than MiMo-V2-Pro?

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 30.5 on the Noometry Index.

Which is cheaper, GPT-4 Turbo or MiMo-V2-Pro?

MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GPT-4 Turbo lists at $10 and $30.

Is GPT-4 Turbo or MiMo-V2-Pro better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 128K.

How many benchmarks do GPT-4 Turbo and MiMo-V2-Pro share?

17 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and MiMo-V2-Pro has 23.

Related comparisons

Go deeper