Noometry

Model comparison

Claude 3 Haiku vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 25.9 on the Noometry Index.

Last verified . 23 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Qwen3.8 Max in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.8 Max leads 73.2 to 9.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 100% for Qwen3.8 Max.

Side by side

Claude 3 HaikuQwen3.8 Max
ProviderAnthropicAlibaba (Qwen)
Noometry Index25.956.8
Released2024-03-072026-08-02
WeightsProprietaryProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3739

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

Category by category

Coding Qwen3.8 Max leads

Claude 3 Haiku: 26.4 (#325), Qwen3.8 Max: 53.5 (#29)

BenchmarkClaude 3 HaikuQwen3.8 Max
LMArena Coding11991502
DeepSWE—57.5%
LMArena WebDev—1674
FrontierSWE—17.8%
SciCode—53.2%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Qwen3.8 Max: 45.4 (#14)

BenchmarkClaude 3 HaikuQwen3.8 Max
APEX-Agents—63.3%
τ²-bench Banking—55.1%
GDP.pdf—23.2%

Reasoning Qwen3.8 Max leads

Claude 3 Haiku: 16.3 (#307), Qwen3.8 Max: 54.4 (#26)

BenchmarkClaude 3 HaikuQwen3.8 Max
LMArena Hard Prompts11741496
DTBench50.1%92%
LMCA8.8%46.2%
Epoch Capabilities Index118.35156.41
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—88.3%
CritPt—20%
Chess Puzzles—40%
Mystery Game Puzzles—38%
ForecastBench53.2—
WinoGrande74.2%—

Math Qwen3.8 Max leads

Claude 3 Haiku: 9.8 (#319), Qwen3.8 Max: 73.2 (#20)

BenchmarkClaude 3 HaikuQwen3.8 Max
OTIS Mock AIME 2024-20251.8%100%
LMArena Math11881499
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
ProofBench—58%
MATH Level 514.9%—

Knowledge Qwen3.8 Max leads

Claude 3 Haiku: 17.3 (#285), Qwen3.8 Max: 61.7 (#27)

BenchmarkClaude 3 HaikuQwen3.8 Max
GPQA Diamond36.3%92.7%
LMArena Expert11481507
SimpleQA Verified—47.3%
Confabulations34.2%—
MMLU73.8%—

Multimodal Qwen3.8 Max leads

Claude 3 Haiku: 23.6 (#128), Qwen3.8 Max: 37.2 (#75)

BenchmarkClaude 3 HaikuQwen3.8 Max
LMArena Vision9501314
Furniture Assembly—20%
ScienceQA72%—

Multilingual Qwen3.8 Max leads

Claude 3 Haiku: 36.0 (#243), Qwen3.8 Max: 56.7 (#18)

BenchmarkClaude 3 HaikuQwen3.8 Max
LMArena Non-English11781472
LMArena Chinese11551538
LMArena French11951503
LMArena German11741483
LMArena Japanese11021467
LMArena Korean11091461
LMArena Russian12041481
LMArena Spanish11661492

Instruction Following Qwen3.8 Max leads

Claude 3 Haiku: 61.3 (#247), Qwen3.8 Max: 77.6 (#17)

BenchmarkClaude 3 HaikuQwen3.8 Max
LMArena Instruction Following11731479

Long Context Qwen3.8 Max leads

Claude 3 Haiku: 36.1 (#237), Qwen3.8 Max: 45.6 (#31)

BenchmarkClaude 3 HaikuQwen3.8 Max
LMArena Longer Query11901489

Writing & Preference Qwen3.8 Max leads

Claude 3 Haiku: 29.7 (#291), Qwen3.8 Max: 67.1 (#30)

BenchmarkClaude 3 HaikuQwen3.8 Max
LMArena Text11951483
LMArena Creative Writing11571479
LMArena Multi-Turn11901489
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Qwen3.8 Max share?

23 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper