Noometry

Model comparison

GPT-4 vs MiMo-V2.5-Pro

MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 29.1 on the Noometry Index.

Last verified . 20 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

MiMo-V2.5-Pro Xiaomi

45.2

Rank #74 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GPT-4 scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.3 to 34.9.
  • The biggest single-benchmark swing is DTBench: 62.7% for GPT-4 and 84.5% for MiMo-V2.5-Pro.
  • MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $30 / $60 for GPT-4.
  • MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 8K.
  • MiMo-V2.5-Pro has downloadable open weights; the other is API-only.

Side by side

GPT-4MiMo-V2.5-Pro
ProviderOpenAIXiaomi
Noometry Index29.145.2
Released2023-03-142026-04-22
WeightsProprietaryOpen
Context window8K1.05M
Max output8K131K
Input $ / M tokens$30$0.43
Output $ / M tokens$60$0.87
Results tracked3827

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

Category by category

Coding MiMo-V2.5-Pro leads

GPT-4: 31.6 (#283), MiMo-V2.5-Pro: 47.4 (#60)

BenchmarkGPT-4MiMo-V2.5-Pro
LMArena Coding12541503
LMArena WebDev—1479
SciCode—50.2%
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
ALE-Bench—899.8
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, MiMo-V2.5-Pro: —

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

Reasoning MiMo-V2.5-Pro leads

GPT-4: 17.8 (#289), MiMo-V2.5-Pro: 26.8 (#130)

BenchmarkGPT-4MiMo-V2.5-Pro
LMArena Hard Prompts12411488
DTBench62.7%84.5%
LMCA17.1%29.5%
NYT Connections (extended)—34.4%
CritPt—4%
Chess Puzzles4%—
Mystery Game Puzzles12%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math MiMo-V2.5-Pro leads

GPT-4: 10.8 (#309), MiMo-V2.5-Pro: 40.0 (#96)

BenchmarkGPT-4MiMo-V2.5-Pro
LMArena Math12691481
OTIS Mock AIME 2024-20251.1%—
ProofBench—22%
MATH Level 523%—
GSM8K92%—

Knowledge MiMo-V2.5-Pro leads

GPT-4: 18.4 (#282), MiMo-V2.5-Pro: 42.2 (#98)

BenchmarkGPT-4MiMo-V2.5-Pro
LMArena Expert12111503
GPQA Diamond35.7%—
MMLU86.4%—
TriviaQA84.8%—

Multilingual MiMo-V2.5-Pro leads

GPT-4: 40.6 (#215), MiMo-V2.5-Pro: 55.1 (#34)

BenchmarkGPT-4MiMo-V2.5-Pro
LMArena Non-English12461449
LMArena Chinese12421507
LMArena French12831488
LMArena German12511458
LMArena Japanese12091412
LMArena Korean11841437
LMArena Russian12511450
LMArena Spanish12611471

Instruction Following MiMo-V2.5-Pro leads

GPT-4: 65.3 (#222), MiMo-V2.5-Pro: 77.5 (#21)

BenchmarkGPT-4MiMo-V2.5-Pro
LMArena Instruction Following12411477

Long Context MiMo-V2.5-Pro leads

GPT-4: 37.7 (#212), MiMo-V2.5-Pro: 45.4 (#37)

BenchmarkGPT-4MiMo-V2.5-Pro
LMArena Longer Query12441483

Writing & Preference MiMo-V2.5-Pro leads

GPT-4: 34.9 (#268), MiMo-V2.5-Pro: 65.3 (#49)

BenchmarkGPT-4MiMo-V2.5-Pro
LMArena Text12631465
LMArena Creative Writing12441440
EQ-Bench Creative Writing7521493
LMArena Multi-Turn12571477
EQ-Bench 4—1208

Frequently asked questions

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

MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 29.1 on the Noometry Index.

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

MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GPT-4 lists at $30 and $60.

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

MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

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

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

20 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and MiMo-V2.5-Pro has 27.

Related comparisons

Go deeper