Noometry

Model comparison

GPT-4 Turbo vs MiMo-V2-Omni

MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 30.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

MiMo-V2-Omni Xiaomi

42.9

Rank #91 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and MiMo-V2-Omni in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiMo-V2-Omni leads 36.4 to 8.6.
  • MiMo-V2-Omni is cheaper at $0.14 / $0.28 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • MiMo-V2-Omni accepts more context: 262K tokens versus 128K.

Side by side

GPT-4 TurboMiMo-V2-Omni
ProviderOpenAIXiaomi
Noometry Index30.342.9
Released2023-11-062026-03-18
WeightsProprietaryProprietary
Context window128K262K
Max output4K131K
Input $ / M tokens$10$0.14
Output $ / M tokens$30$0.28
Results tracked3618

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

Category by category

Coding MiMo-V2-Omni leads

GPT-4 Turbo: 33.4 (#247), MiMo-V2-Omni: 42.7 (#87)

BenchmarkGPT-4 TurboMiMo-V2-Omni
LMArena Coding12681467
WeirdML18%—
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, MiMo-V2-Omni: —

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

Reasoning MiMo-V2-Omni leads

GPT-4 Turbo: 14.9 (#311), MiMo-V2-Omni: 28.6 (#86)

BenchmarkGPT-4 TurboMiMo-V2-Omni
LMArena Hard Prompts12511445
SimpleBench25.1%—
Chess Puzzles6%—
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math MiMo-V2-Omni leads

GPT-4 Turbo: 8.6 (#316), MiMo-V2-Omni: 36.4 (#112)

BenchmarkGPT-4 TurboMiMo-V2-Omni
LMArena Math12721432
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
MATH Level 546.7%—

Knowledge MiMo-V2-Omni leads

GPT-4 Turbo: 24.3 (#263), MiMo-V2-Omni: 39.9 (#114)

BenchmarkGPT-4 TurboMiMo-V2-Omni
LMArena Expert12231449
GPQA Diamond46.6%—
Confabulations28.4%—
MMLU81.3%—

Multimodal MiMo-V2-Omni leads

GPT-4 Turbo: 30.0 (#104), MiMo-V2-Omni: 37.9 (#62)

BenchmarkGPT-4 TurboMiMo-V2-Omni
LMArena Vision10901228

Multilingual MiMo-V2-Omni leads

GPT-4 Turbo: 40.7 (#211), MiMo-V2-Omni: 52.0 (#97)

BenchmarkGPT-4 TurboMiMo-V2-Omni
LMArena Non-English12451404
LMArena Chinese12421469
LMArena French12751448
LMArena German12591398
LMArena Japanese11941318
LMArena Korean11871355
LMArena Russian12591412
LMArena Spanish12601432

Instruction Following MiMo-V2-Omni leads

GPT-4 Turbo: 66.0 (#211), MiMo-V2-Omni: 75.4 (#62)

BenchmarkGPT-4 TurboMiMo-V2-Omni
LMArena Instruction Following12501428

Long Context MiMo-V2-Omni leads

GPT-4 Turbo: 38.0 (#200), MiMo-V2-Omni: 44.1 (#72)

BenchmarkGPT-4 TurboMiMo-V2-Omni
LMArena Longer Query12541442

Writing & Preference MiMo-V2-Omni leads

GPT-4 Turbo: 47.9 (#201), MiMo-V2-Omni: 61.6 (#83)

BenchmarkGPT-4 TurboMiMo-V2-Omni
LMArena Text12721424
LMArena Creative Writing12691393
LMArena Multi-Turn12671446

Frequently asked questions

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

MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 30.3 on the Noometry Index.

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

MiMo-V2-Omni is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; GPT-4 Turbo lists at $10 and $30.

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

MiMo-V2-Omni scores higher on coding benchmarks: 42.7 versus 33.4 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2-Omni does, with 262K tokens against 128K.

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

18 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and MiMo-V2-Omni has 18.

Related comparisons

Go deeper