Model comparison
Claude Haiku 4.5 vs Gemini 2.0 Flash-Lite
Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 37.3 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Gemini 2.0 Flash-Lite in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 4.5 leads 43.0 to 31.8.
- The biggest single-benchmark swing is DTBench: 73.6% for Claude Haiku 4.5 and 52.5% for Gemini 2.0 Flash-Lite.
Side by side
| Claude Haiku 4.5 | Gemini 2.0 Flash-Lite | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.3 | 37.3 |
| Released | 2025-10-15 | 2025-02-05 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.9 (#71), Gemini 2.0 Flash-Lite: 37.4 (#181)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Coding | 1454 | 1322 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| LiveBench Coding | — | 47.1% |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.5 (#50), Gemini 2.0 Flash-Lite: —
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash-Lite |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Gemini 2.0 Flash-Lite leads
Claude Haiku 4.5: 15.1 (#310), Gemini 2.0 Flash-Lite: 21.2 (#203)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1324 |
| DTBench | 73.6% | 52.5% |
| ForecastBench | 61.4 | 57.1 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LiveBench Reasoning | — | 50.1% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.42 | — |
| LiveBench | — | 54.3% |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.0 (#69), Gemini 2.0 Flash-Lite: 31.8 (#192)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash-Lite |
|---|---|---|
| Omni-MATH | 56.1% | 37.4% |
| LMArena Math | 1395 | 1309 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| LiveBench Math | — | 58.1% |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.6 (#146), Gemini 2.0 Flash-Lite: 34.6 (#185)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash-Lite |
|---|---|---|
| MMLU-Pro | 77.7% | 72% |
| GPQA (HELM) | 60.5% | 50% |
| LMArena Expert | 1443 | 1305 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| Vectara Hallucination Rate | 9.8% | — |
Multimodal Gemini 2.0 Flash-Lite leads
Claude Haiku 4.5: 27.0 (#111), Gemini 2.0 Flash-Lite: 30.6 (#103)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Vision | — | 1100 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 50.1 (#124), Gemini 2.0 Flash-Lite: 46.2 (#156)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1376 | 1323 |
| LMArena Chinese | 1415 | 1339 |
| LMArena French | 1408 | 1346 |
| LMArena German | 1377 | 1306 |
| LMArena Japanese | 1339 | 1302 |
| LMArena Korean | 1346 | 1325 |
| LMArena Russian | 1380 | 1328 |
| LMArena Spanish | 1420 | 1313 |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.6 (#144), Gemini 2.0 Flash-Lite: 70.6 (#158)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash-Lite |
|---|---|---|
| IFEval | 80.1% | 82.4% |
| LMArena Instruction Following | 1414 | 1305 |
| LiveBench Instruction Following | — | 78.3% |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#86), Gemini 2.0 Flash-Lite: 40.1 (#155)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Longer Query | 1427 | 1321 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 58.1 (#119), Gemini 2.0 Flash-Lite: 51.9 (#172)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Text | 1396 | 1330 |
| LMArena Creative Writing | 1371 | 1319 |
| WildBench | 83.9% | 79% |
| LMArena Multi-Turn | 1409 | 1307 |
| EQ-Bench 4 | 1064 | — |
| LiveBench Language | — | 34.3% |
Frequently asked questions
Is Claude Haiku 4.5 better than Gemini 2.0 Flash-Lite?
Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 37.3 on the Noometry Index.
Is Claude Haiku 4.5 or Gemini 2.0 Flash-Lite better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 37.4 in the Noometry coding category.
How many benchmarks do Claude Haiku 4.5 and Gemini 2.0 Flash-Lite share?
24 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemini 2.0 Flash-Lite has 32.