Model comparison
Claude 3 Haiku vs Gemini 3.5 Flash
Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 25.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Gemini 3.5 Flash in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.5 Flash leads 60.7 to 9.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 95.6% for Gemini 3.5 Flash.
Side by side
| Claude 3 Haiku | Gemini 3.5 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 25.9 | 54.2 |
| Released | 2024-03-07 | 2026-05-19 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $9 |
| Results tracked | 37 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.5 Flash leads
Claude 3 Haiku: 26.4 (#325), Gemini 3.5 Flash: 49.4 (#49)
| Benchmark | Claude 3 Haiku | Gemini 3.5 Flash |
|---|---|---|
| WeirdML | 9.8% | 62.6% |
| LMArena Coding | 1199 | 1492 |
| SWE-bench Verified | — | 79.3% |
| DeepSWE | — | 37.4% |
| LMArena WebDev | — | 1499 |
| SciCode | — | 53.1% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 911.02 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Agentic & Tool Use Not comparable
Claude 3 Haiku: —, Gemini 3.5 Flash: 24.7 (#114)
| Benchmark | Claude 3 Haiku | Gemini 3.5 Flash |
|---|---|---|
| APEX-Agents | — | 27.5% |
| GBAEval | — | 6.7% |
| GDP.pdf | — | 14% |
| Vending-Bench 2 | — | 5,396 |
Reasoning Gemini 3.5 Flash leads
Claude 3 Haiku: 16.3 (#307), Gemini 3.5 Flash: 62.8 (#18)
| Benchmark | Claude 3 Haiku | Gemini 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1488 |
| DTBench | 50.1% | 94.7% |
| LMCA | 8.8% | 47.1% |
| Epoch Capabilities Index | 118.35 | 154.46 |
| ForecastBench | 53.2 | 59 |
| ARC-AGI-2 | — | 72.1% |
| SimpleBench | — | 76.7% |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 92.6% |
| ARC-AGI-1 | — | 92.5% |
| CritPt | — | 13.1% |
| Chess Puzzles | — | 50% |
| EnigmaEval | — | 25.4% |
| EBR-Bench | — | 4.8% |
| Mystery Game Puzzles | — | 32% |
| Surface Evolver Bench | — | 58.1% |
| WinoGrande | 74.2% | — |
Math Gemini 3.5 Flash leads
Claude 3 Haiku: 9.8 (#319), Gemini 3.5 Flash: 60.7 (#36)
| Benchmark | Claude 3 Haiku | Gemini 3.5 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 95.6% |
| LMArena Math | 1188 | 1504 |
| FrontierMath (Tiers 1-3) | — | 62.8% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 76.3% |
| ProofBench | — | 31% |
| MATH Level 5 | 14.9% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Gemini 3.5 Flash leads
Claude 3 Haiku: 17.3 (#285), Gemini 3.5 Flash: 66.3 (#11)
| Benchmark | Claude 3 Haiku | Gemini 3.5 Flash |
|---|---|---|
| GPQA Diamond | 36.3% | 92.8% |
| LMArena Expert | 1148 | 1495 |
| SimpleQA Verified | — | 66.2% |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Gemini 3.5 Flash leads
Claude 3 Haiku: 23.6 (#128), Gemini 3.5 Flash: 45.7 (#15)
| Benchmark | Claude 3 Haiku | Gemini 3.5 Flash |
|---|---|---|
| LMArena Vision | 950 | 1310 |
| Blueprint-Bench 2 | — | 33.6% |
| LMArena Document | — | 1463 |
| ScienceQA | 72% | — |
Multilingual Gemini 3.5 Flash leads
Claude 3 Haiku: 36.0 (#243), Gemini 3.5 Flash: 57.0 (#13)
| Benchmark | Claude 3 Haiku | Gemini 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1178 | 1476 |
| LMArena Chinese | 1155 | 1526 |
| LMArena French | 1195 | 1490 |
| LMArena German | 1174 | 1492 |
| LMArena Japanese | 1102 | 1486 |
| LMArena Korean | 1109 | 1451 |
| LMArena Russian | 1204 | 1493 |
| LMArena Spanish | 1166 | 1480 |
Instruction Following Gemini 3.5 Flash leads
Claude 3 Haiku: 61.3 (#247), Gemini 3.5 Flash: 77.0 (#30)
| Benchmark | Claude 3 Haiku | Gemini 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1173 | 1467 |
Long Context Gemini 3.5 Flash leads
Claude 3 Haiku: 36.1 (#237), Gemini 3.5 Flash: 45.4 (#38)
| Benchmark | Claude 3 Haiku | Gemini 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1190 | 1482 |
Writing & Preference Gemini 3.5 Flash leads
Claude 3 Haiku: 29.7 (#291), Gemini 3.5 Flash: 65.5 (#47)
| Benchmark | Claude 3 Haiku | Gemini 3.5 Flash |
|---|---|---|
| LMArena Text | 1195 | 1482 |
| LMArena Creative Writing | 1157 | 1470 |
| LMArena Multi-Turn | 1190 | 1481 |
| EQ-Bench Creative Writing | 717 | — |
| EQ-Bench 4 | — | 1087 |
Frequently asked questions
Is Claude 3 Haiku better than Gemini 3.5 Flash?
Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Gemini 3.5 Flash better for coding?
Gemini 3.5 Flash scores higher on coding benchmarks: 49.4 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Gemini 3.5 Flash share?
25 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemini 3.5 Flash has 54.