Noometry

Model comparison

Claude 3 Haiku vs GPT-6.1 Sol

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 25.9 on the Noometry Index.

Last verified . 16 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GPT-6.1 Sol in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 9.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 100% for GPT-6.1 Sol.

Side by side

Claude 3 HaikuGPT-6.1 Sol
ProviderAnthropicOpenAI
Noometry Index25.965.6
Released2024-03-072026-09-29
WeightsProprietaryProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$2
Output $ / M tokens—$10
Results tracked3734

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

Category by category

Coding GPT-6.1 Sol leads

Claude 3 Haiku: 26.4 (#325), GPT-6.1 Sol: 63.2 (#8)

BenchmarkClaude 3 HaikuGPT-6.1 Sol
LMArena Coding11991487
DeepSWE—75.2%
FrontierCode—50.2%
LMArena WebDev—1755
SciCode—55.8%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, GPT-6.1 Sol: 39.6 (#26)

BenchmarkClaude 3 HaikuGPT-6.1 Sol
APEX-Agents—60%
GDP.pdf—32%

Reasoning GPT-6.1 Sol leads

Claude 3 Haiku: 16.3 (#307), GPT-6.1 Sol: 81.9 (#2)

BenchmarkClaude 3 HaikuGPT-6.1 Sol
LMArena Hard Prompts11741466
Epoch Capabilities Index118.35166.09
ARC-AGI-2—94.2%
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—95.5%
ARC-AGI-1—98.5%
CritPt—31.7%
Chess Puzzles—61%
EBR-Bench—54.3%
Mystery Game Puzzles—80%
DTBench50.1%—
LMCA8.8%—
ForecastBench53.2—
WinoGrande74.2%—

Math GPT-6.1 Sol leads

Claude 3 Haiku: 9.8 (#319), GPT-6.1 Sol: 93.7 (#1)

BenchmarkClaude 3 HaikuGPT-6.1 Sol
OTIS Mock AIME 2024-20251.8%100%
LMArena Math11881464
FrontierMath (Tiers 1-3)—93.7%
FrontierMath Tier 4—100%
ProofBench—99%
MATH Level 514.9%—

Knowledge GPT-6.1 Sol leads

Claude 3 Haiku: 17.3 (#285), GPT-6.1 Sol: 71.8 (#4)

BenchmarkClaude 3 HaikuGPT-6.1 Sol
GPQA Diamond36.3%95.4%
LMArena Expert11481502
SimpleQA Verified—73.9%
Confabulations34.2%—
MMLU73.8%—

Multimodal GPT-6.1 Sol leads

Claude 3 Haiku: 23.6 (#128), GPT-6.1 Sol: 52.7 (#5)

BenchmarkClaude 3 HaikuGPT-6.1 Sol
LMArena Vision9501288
Furniture Assembly—80%
ScienceQA72%—

Multilingual GPT-6.1 Sol leads

Claude 3 Haiku: 36.0 (#243), GPT-6.1 Sol: 54.3 (#46)

BenchmarkClaude 3 HaikuGPT-6.1 Sol
LMArena Non-English11781438
LMArena Chinese11551477
LMArena Russian12041455
LMArena French1195—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1109—
LMArena Spanish1166—

Instruction Following GPT-6.1 Sol leads

Claude 3 Haiku: 61.3 (#247), GPT-6.1 Sol: 77.0 (#29)

BenchmarkClaude 3 HaikuGPT-6.1 Sol
LMArena Instruction Following11731468

Long Context GPT-6.1 Sol leads

Claude 3 Haiku: 36.1 (#237), GPT-6.1 Sol: 44.9 (#54)

BenchmarkClaude 3 HaikuGPT-6.1 Sol
LMArena Longer Query11901465

Writing & Preference GPT-6.1 Sol leads

Claude 3 Haiku: 29.7 (#291), GPT-6.1 Sol: 63.6 (#63)

BenchmarkClaude 3 HaikuGPT-6.1 Sol
LMArena Text11951447
LMArena Creative Writing11571432
LMArena Multi-Turn11901449
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than GPT-6.1 Sol?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or GPT-6.1 Sol better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and GPT-6.1 Sol share?

16 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GPT-6.1 Sol has 34.

Related comparisons

Go deeper