Model comparison
Claude 3 Haiku vs Gemini 2.5 Flash
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 25.9 on the Noometry Index.
Last verified . 27 shared benchmarks.
GoogleSummary
- They share 27 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Gemini 2.5 Flash in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash leads 39.9 to 9.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 73.1% for Gemini 2.5 Flash.
Side by side
| Claude 3 Haiku | Gemini 2.5 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 25.9 | 39.3 |
| Released | 2024-03-07 | 2025-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 37 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
Claude 3 Haiku: 26.4 (#325), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | Claude 3 Haiku | Gemini 2.5 Flash |
|---|---|---|
| WeirdML | 9.8% | 41.9% |
| LMArena Coding | 1199 | 1424 |
| SWE-bench Verified (bash only) | — | 28.7% |
| Aider Polyglot | — | 55.1% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 661.88 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Agentic & Tool Use Not comparable
Claude 3 Haiku: —, Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | Claude 3 Haiku | Gemini 2.5 Flash |
|---|---|---|
| Terminal-Bench | — | 17.1% |
| Berkeley Function Calling Leaderboard | — | 56.2% |
| TheAgentCompany | — | 41.1% |
| BALROG | — | 33.5% |
| Vending-Bench 2 | — | 548.84 |
Reasoning Gemini 2.5 Flash leads
Claude 3 Haiku: 16.3 (#307), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | Claude 3 Haiku | Gemini 2.5 Flash |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 56.8% |
| LMArena Hard Prompts | 1174 | 1422 |
| DTBench | 50.1% | 76.5% |
| LMCA | 8.8% | 27.5% |
| Epoch Capabilities Index | 118.35 | 143.03 |
| ForecastBench | 53.2 | 60.6 |
| ARC-AGI-2 | — | 2.5% |
| SimpleBench | — | 41.2% |
| ARC-AGI-1 | — | 33.3% |
| CritPt | — | 1.1% |
| EnigmaEval | — | 2.7% |
| WinoGrande | 74.2% | — |
Math Gemini 2.5 Flash leads
Claude 3 Haiku: 9.8 (#319), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | Claude 3 Haiku | Gemini 2.5 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 73.1% |
| LMArena Math | 1188 | 1415 |
| Omni-MATH | — | 38.5% |
| MATH Level 5 | 14.9% | — |
| FrontierMath (Feb 2025 set) | — | 4.8% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 2.5 Flash leads
Claude 3 Haiku: 17.3 (#285), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | Claude 3 Haiku | Gemini 2.5 Flash |
|---|---|---|
| Confabulations | 34.2% | 16.8% |
| LMArena Expert | 1148 | 1426 |
| GPQA Diamond | 36.3% | — |
| Humanity's Last Exam | — | 12.1% |
| MMLU-Pro | — | 63.9% |
| Vectara Hallucination Rate | — | 7.8% |
| GPQA (HELM) | — | 39% |
| MMLU | 73.8% | — |
Multimodal Gemini 2.5 Flash leads
Claude 3 Haiku: 23.6 (#128), Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | Claude 3 Haiku | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | 950 | 1253 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| ScienceQA | 72% | — |
| SpatialViz-Bench | — | 36.9% |
Multilingual Gemini 2.5 Flash leads
Claude 3 Haiku: 36.0 (#243), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | Claude 3 Haiku | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1178 | 1409 |
| LMArena Chinese | 1155 | 1450 |
| LMArena French | 1195 | 1433 |
| LMArena German | 1174 | 1418 |
| LMArena Japanese | 1102 | 1405 |
| LMArena Korean | 1109 | 1385 |
| LMArena Russian | 1204 | 1415 |
| LMArena Spanish | 1166 | 1421 |
Instruction Following Gemini 2.5 Flash leads
Claude 3 Haiku: 61.3 (#247), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | Claude 3 Haiku | Gemini 2.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1173 | 1405 |
| IFEval | — | 89.8% |
Long Context Gemini 2.5 Flash leads
Claude 3 Haiku: 36.1 (#237), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | Claude 3 Haiku | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1190 | 1419 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Gemini 2.5 Flash leads
Claude 3 Haiku: 29.7 (#291), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | Claude 3 Haiku | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1195 | 1417 |
| LMArena Creative Writing | 1157 | 1400 |
| EQ-Bench Creative Writing | 717 | 1137 |
| LMArena Multi-Turn | 1190 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| WildBench | — | 81.7% |
Frequently asked questions
Is Claude 3 Haiku better than Gemini 2.5 Flash?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Gemini 2.5 Flash better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Gemini 2.5 Flash share?
27 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemini 2.5 Flash has 54.