Noometry

Model comparison

GPT-4 vs MiMo-V2.5

MiMo-V2.5 is the stronger model overall, scoring 43.4 to 29.1 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

MiMo-V2.5 Xiaomi

43.4

Rank #93 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-4 scores higher in 0 categories and MiMo-V2.5 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where MiMo-V2.5 leads 61.6 to 34.9.
  • MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $30 / $60 for GPT-4.
  • MiMo-V2.5 accepts more context: 1.05M tokens versus 8K.
  • MiMo-V2.5 has downloadable open weights; the other is API-only.

Side by side

GPT-4MiMo-V2.5
ProviderOpenAIXiaomi
Noometry Index29.143.4
Released2023-03-142026-04-22
WeightsProprietaryOpen
Context window8K1.05M
Max output8K131K
Input $ / M tokens$30$0.14
Output $ / M tokens$60$0.28
Results tracked3823

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

Category by category

Coding MiMo-V2.5 leads

GPT-4: 31.6 (#283), MiMo-V2.5: 43.9 (#81)

BenchmarkGPT-4MiMo-V2.5
LMArena Coding12541469
LMArena WebDev—1438
SciCode—43.1%
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
ALE-Bench—513.95
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, MiMo-V2.5: —

BenchmarkGPT-4MiMo-V2.5
METR Time Horizons36.1%—

Reasoning MiMo-V2.5 leads

GPT-4: 17.8 (#289), MiMo-V2.5: 28.6 (#101)

BenchmarkGPT-4MiMo-V2.5
LMArena Hard Prompts12411450
CritPt—3.7%
Chess Puzzles4%—
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math MiMo-V2.5 leads

GPT-4: 10.8 (#309), MiMo-V2.5: 36.8 (#163)

BenchmarkGPT-4MiMo-V2.5
LMArena Math12691436
OTIS Mock AIME 2024-20251.1%—
ProofBench—16%
MATH Level 523%—
GSM8K92%—

Knowledge MiMo-V2.5 leads

GPT-4: 18.4 (#282), MiMo-V2.5: 40.8 (#115)

BenchmarkGPT-4MiMo-V2.5
LMArena Expert12111460
GPQA Diamond35.7%—
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, MiMo-V2.5: 39.8 (#54)

BenchmarkGPT-4MiMo-V2.5
LMArena Vision—1247

Multilingual MiMo-V2.5 leads

GPT-4: 40.6 (#215), MiMo-V2.5: 51.9 (#99)

BenchmarkGPT-4MiMo-V2.5
LMArena Non-English12461404
LMArena Chinese12421468
LMArena French12831447
LMArena German12511421
LMArena Japanese12091306
LMArena Korean11841363
LMArena Russian12511395
LMArena Spanish12611416

Instruction Following MiMo-V2.5 leads

GPT-4: 65.3 (#222), MiMo-V2.5: 75.5 (#60)

BenchmarkGPT-4MiMo-V2.5
LMArena Instruction Following12411434

Long Context MiMo-V2.5 leads

GPT-4: 37.7 (#212), MiMo-V2.5: 44.2 (#73)

BenchmarkGPT-4MiMo-V2.5
LMArena Longer Query12441445

Writing & Preference MiMo-V2.5 leads

GPT-4: 34.9 (#268), MiMo-V2.5: 61.6 (#86)

BenchmarkGPT-4MiMo-V2.5
LMArena Text12631428
LMArena Creative Writing12441393
LMArena Multi-Turn12571445
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than MiMo-V2.5?

MiMo-V2.5 is the stronger model overall, scoring 43.4 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or MiMo-V2.5?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 8K.

How many benchmarks do GPT-4 and MiMo-V2.5 share?

17 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and MiMo-V2.5 has 23.

Related comparisons

Go deeper