Noometry

Model comparison

Claude 3.5 Haiku vs MiMo-V2.6-Pro

MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 28.9 on the Noometry Index.

Last verified . 13 shared benchmarks.

Claude 3.5 Haiku Anthropic

28.9

Rank #309 Confirmed

MiMo-V2.6-Pro Xiaomi

46.7

Rank #55 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and MiMo-V2.6-Pro in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiMo-V2.6-Pro leads 43.0 to 18.7.
  • MiMo-V2.6-Pro has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuMiMo-V2.6-Pro
ProviderAnthropicXiaomi
Noometry Index28.946.7
Released2024-10-222026-09-22
WeightsProprietaryOpen
Context window—1.05M
Max output—131K
Input $ / M tokens—$0.43
Output $ / M tokens—$0.87
Results tracked4914

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

Category by category

Coding MiMo-V2.6-Pro leads

Claude 3.5 Haiku: 32.6 (#258), MiMo-V2.6-Pro: 53.2 (#27)

BenchmarkClaude 3.5 HaikuMiMo-V2.6-Pro
LMArena Coding12871538
Aider Polyglot28%—
LMArena WebDev—1618
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 27.7 (#90), MiMo-V2.6-Pro: —

BenchmarkClaude 3.5 HaikuMiMo-V2.6-Pro
BALROG19.3%—

Reasoning MiMo-V2.6-Pro leads

Claude 3.5 Haiku: 17.1 (#286), MiMo-V2.6-Pro: 30.4 (#76)

BenchmarkClaude 3.5 HaikuMiMo-V2.6-Pro
LMArena Hard Prompts12511511
CritPt0%—
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math MiMo-V2.6-Pro leads

Claude 3.5 Haiku: 13.7 (#294), MiMo-V2.6-Pro: 37.9 (#91)

BenchmarkClaude 3.5 HaikuMiMo-V2.6-Pro
LMArena Math12441497
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge MiMo-V2.6-Pro leads

Claude 3.5 Haiku: 18.7 (#276), MiMo-V2.6-Pro: 43.0 (#85)

BenchmarkClaude 3.5 HaikuMiMo-V2.6-Pro
LMArena Expert12081548
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal MiMo-V2.6-Pro leads

Claude 3.5 Haiku: 26.3 (#113), MiMo-V2.6-Pro: 40.2 (#40)

BenchmarkClaude 3.5 HaikuMiMo-V2.6-Pro
LMArena Vision10921265
GeoBench34%—

Multilingual MiMo-V2.6-Pro leads

Claude 3.5 Haiku: 40.2 (#213), MiMo-V2.6-Pro: 57.0 (#15)

BenchmarkClaude 3.5 HaikuMiMo-V2.6-Pro
LMArena Non-English12381474
LMArena Chinese12291532
LMArena Russian12531481
LMArena French1262—
LMArena German1237—
LMArena Japanese1175—
LMArena Korean1172—
LMArena Spanish1261—

Instruction Following MiMo-V2.6-Pro leads

Claude 3.5 Haiku: 63.1 (#229), MiMo-V2.6-Pro: 78.2 (#10)

BenchmarkClaude 3.5 HaikuMiMo-V2.6-Pro
LMArena Instruction Following12411490
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context MiMo-V2.6-Pro leads

Claude 3.5 Haiku: 38.3 (#195), MiMo-V2.6-Pro: 46.0 (#26)

BenchmarkClaude 3.5 HaikuMiMo-V2.6-Pro
LMArena Longer Query12611500

Writing & Preference MiMo-V2.6-Pro leads

Claude 3.5 Haiku: 42.9 (#228), MiMo-V2.6-Pro: 66.9 (#32)

BenchmarkClaude 3.5 HaikuMiMo-V2.6-Pro
LMArena Text12551491
LMArena Creative Writing12331465
LMArena Multi-Turn12651463
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 28.9 on the Noometry Index.

Is Claude 3.5 Haiku or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 53.2 versus 32.6 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and MiMo-V2.6-Pro share?

13 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and MiMo-V2.6-Pro has 14.

Related comparisons

Go deeper