Model comparison
Claude 3.5 Haiku vs Gemini 2.5 Flash-Lite
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 28.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and Gemini 2.5 Flash-Lite in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash-Lite leads 35.5 to 13.7.
- The biggest single-benchmark swing is Omni-MATH: 22.4% for Claude 3.5 Haiku and 48% for Gemini 2.5 Flash-Lite.
Side by side
| Claude 3.5 Haiku | Gemini 2.5 Flash-Lite | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 28.9 | 36.4 |
| Released | 2024-10-22 | 2025-06-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 49 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash-Lite leads
Claude 3.5 Haiku: 32.6 (#258), Gemini 2.5 Flash-Lite: 38.0 (#167)
| Benchmark | Claude 3.5 Haiku | Gemini 2.5 Flash-Lite |
|---|---|---|
| WeirdML | 30.7% | 35.2% |
| LMArena Coding | 1287 | 1373 |
| Aider Polyglot | 28% | — |
| SciCode | 27.4% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 325.9 |
Agentic & Tool Use Too close to call
Claude 3.5 Haiku: 27.7 (#90), Gemini 2.5 Flash-Lite: 27.8 (#89)
| Benchmark | Claude 3.5 Haiku | Gemini 2.5 Flash-Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 36.9% |
| BALROG | 19.3% | — |
Reasoning Gemini 2.5 Flash-Lite leads
Claude 3.5 Haiku: 17.1 (#286), Gemini 2.5 Flash-Lite: 21.5 (#196)
| Benchmark | Claude 3.5 Haiku | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1377 |
| DTBench | 56.7% | 62.8% |
| Epoch Capabilities Index | 127.15 | 133.93 |
| Kagi LLM Benchmark | — | 40.5% |
| CritPt | 0% | — |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 18.1% |
| LiveBench | 43.5% | — |
Math Gemini 2.5 Flash-Lite leads
Claude 3.5 Haiku: 13.7 (#294), Gemini 2.5 Flash-Lite: 35.5 (#144)
| Benchmark | Claude 3.5 Haiku | Gemini 2.5 Flash-Lite |
|---|---|---|
| Omni-MATH | 22.4% | 48% |
| LMArena Math | 1244 | 1373 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Gemini 2.5 Flash-Lite leads
Claude 3.5 Haiku: 18.7 (#276), Gemini 2.5 Flash-Lite: 32.1 (#206)
| Benchmark | Claude 3.5 Haiku | Gemini 2.5 Flash-Lite |
|---|---|---|
| MMLU-Pro | 60.5% | 53.7% |
| GPQA (HELM) | 36.3% | 30.9% |
| LMArena Expert | 1208 | 1373 |
| GPQA Diamond | 38.1% | — |
| Confabulations | 36.7% | — |
| Vectara Hallucination Rate | — | 3.3% |
| MMLU | 74.3% | — |
Multimodal Gemini 2.5 Flash-Lite leads
Claude 3.5 Haiku: 26.3 (#113), Gemini 2.5 Flash-Lite: 28.6 (#109)
| Benchmark | Claude 3.5 Haiku | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Vision | 1092 | 1198 |
| GeoBench | 34% | — |
| VPCT | — | 30% |
Multilingual Gemini 2.5 Flash-Lite leads
Claude 3.5 Haiku: 40.2 (#213), Gemini 2.5 Flash-Lite: 49.5 (#129)
| Benchmark | Claude 3.5 Haiku | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1238 | 1369 |
| LMArena Chinese | 1229 | 1404 |
| LMArena French | 1262 | 1388 |
| LMArena German | 1237 | 1390 |
| LMArena Japanese | 1175 | 1359 |
| LMArena Korean | 1172 | 1358 |
| LMArena Russian | 1253 | 1373 |
| LMArena Spanish | 1261 | 1396 |
Instruction Following Gemini 2.5 Flash-Lite leads
Claude 3.5 Haiku: 63.1 (#229), Gemini 2.5 Flash-Lite: 70.2 (#163)
| Benchmark | Claude 3.5 Haiku | Gemini 2.5 Flash-Lite |
|---|---|---|
| IFEval | 79.2% | 81% |
| LMArena Instruction Following | 1241 | 1366 |
| LiveBench Instruction Following | 61.9% | — |
Long Context Claude 3.5 Haiku leads
Claude 3.5 Haiku: 38.3 (#195), Gemini 2.5 Flash-Lite: 33.3 (#257)
| Benchmark | Claude 3.5 Haiku | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Longer Query | 1261 | 1373 |
| Fiction.LiveBench | — | 47.2% |
Writing & Preference Gemini 2.5 Flash-Lite leads
Claude 3.5 Haiku: 42.9 (#228), Gemini 2.5 Flash-Lite: 57.0 (#130)
| Benchmark | Claude 3.5 Haiku | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Text | 1255 | 1379 |
| LMArena Creative Writing | 1233 | 1366 |
| WildBench | 76% | 81.8% |
| LMArena Multi-Turn | 1265 | 1367 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Gemini 2.5 Flash-Lite?
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 28.9 on the Noometry Index.
Is Claude 3.5 Haiku or Gemini 2.5 Flash-Lite better for coding?
Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.0 versus 32.6 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Gemini 2.5 Flash-Lite share?
26 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Gemini 2.5 Flash-Lite has 33.