Model comparison
Claude 3 Haiku vs Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 25.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Gemini 3.1 Flash Lite in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 3.1 Flash Lite leads 60.9 to 29.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 80% for Gemini 3.1 Flash Lite.
Side by side
| Claude 3 Haiku | Gemini 3.1 Flash Lite | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 25.9 | 40.8 |
| Released | 2024-03-07 | 2026-03-03 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $1.50 |
| Results tracked | 37 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Flash Lite leads
Claude 3 Haiku: 26.4 (#325), Gemini 3.1 Flash Lite: 37.8 (#188)
| Benchmark | Claude 3 Haiku | Gemini 3.1 Flash Lite |
|---|---|---|
| WeirdML | 9.8% | 52.2% |
| LMArena Coding | 1199 | 1400 |
| LMArena WebDev | — | 1256 |
| SciCode | — | 41.9% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 797.73 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Agentic & Tool Use Not comparable
Claude 3 Haiku: —, Gemini 3.1 Flash Lite: 30.2 (#79)
| Benchmark | Claude 3 Haiku | Gemini 3.1 Flash Lite |
|---|---|---|
| DeepResearch Bench | — | 37.3% |
Reasoning Gemini 3.1 Flash Lite leads
Claude 3 Haiku: 16.3 (#307), Gemini 3.1 Flash Lite: 22.9 (#186)
| Benchmark | Claude 3 Haiku | Gemini 3.1 Flash Lite |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 67.2% |
| LMArena Hard Prompts | 1174 | 1407 |
| DTBench | 50.1% | 76.8% |
| LMCA | 8.8% | 35% |
| Epoch Capabilities Index | 118.35 | 144.47 |
| ForecastBench | 53.2 | 54.4 |
| NYT Connections (extended) | — | 8.2% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 25% |
| EnigmaEval | — | 3% |
| Thematic Generalization | — | 63.3% |
| WinoGrande | 74.2% | — |
Math Gemini 3.1 Flash Lite leads
Claude 3 Haiku: 9.8 (#319), Gemini 3.1 Flash Lite: 40.7 (#90)
| Benchmark | Claude 3 Haiku | Gemini 3.1 Flash Lite |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 80% |
| LMArena Math | 1188 | 1428 |
| FrontierMath (Tiers 1-3) | — | 27.7% |
| MATH Level 5 | 14.9% | — |
Knowledge Gemini 3.1 Flash Lite leads
Claude 3 Haiku: 17.3 (#285), Gemini 3.1 Flash Lite: 41.9 (#104)
| Benchmark | Claude 3 Haiku | Gemini 3.1 Flash Lite |
|---|---|---|
| GPQA Diamond | 36.3% | 81.8% |
| LMArena Expert | 1148 | 1398 |
| Humanity's Last Exam | — | 8.6% |
| Confabulations | 34.2% | — |
| Vectara Hallucination Rate | — | 8.2% |
| MMLU | 73.8% | — |
Multimodal Gemini 3.1 Flash Lite leads
Claude 3 Haiku: 23.6 (#128), Gemini 3.1 Flash Lite: 39.4 (#60)
| Benchmark | Claude 3 Haiku | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Vision | 950 | 1240 |
| ScienceQA | 72% | — |
Multilingual Gemini 3.1 Flash Lite leads
Claude 3 Haiku: 36.0 (#243), Gemini 3.1 Flash Lite: 52.3 (#86)
| Benchmark | Claude 3 Haiku | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Non-English | 1178 | 1411 |
| LMArena Chinese | 1155 | 1461 |
| LMArena French | 1195 | 1424 |
| LMArena German | 1174 | 1429 |
| LMArena Japanese | 1102 | 1413 |
| LMArena Korean | 1109 | 1392 |
| LMArena Russian | 1204 | 1420 |
| LMArena Spanish | 1166 | 1421 |
Instruction Following Gemini 3.1 Flash Lite leads
Claude 3 Haiku: 61.3 (#247), Gemini 3.1 Flash Lite: 72.7 (#131)
| Benchmark | Claude 3 Haiku | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Instruction Following | 1173 | 1377 |
Long Context Gemini 3.1 Flash Lite leads
Claude 3 Haiku: 36.1 (#237), Gemini 3.1 Flash Lite: 42.5 (#122)
| Benchmark | Claude 3 Haiku | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Longer Query | 1190 | 1394 |
Writing & Preference Gemini 3.1 Flash Lite leads
Claude 3 Haiku: 29.7 (#291), Gemini 3.1 Flash Lite: 60.9 (#94)
| Benchmark | Claude 3 Haiku | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Text | 1195 | 1416 |
| LMArena Creative Writing | 1157 | 1401 |
| LMArena Multi-Turn | 1190 | 1417 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Gemini 3.1 Flash Lite?
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Gemini 3.1 Flash Lite better for coding?
Gemini 3.1 Flash Lite scores higher on coding benchmarks: 37.8 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Gemini 3.1 Flash Lite share?
26 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemini 3.1 Flash Lite has 38.