Model comparison
Claude Haiku 4.5 vs Gemini 2.5 Flash-Lite
Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 11× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
GoogleSummary
- They share 29 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 8 categories and Gemini 2.5 Flash-Lite in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude Haiku 4.5 leads 43.6 to 33.3.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 68.7% for Claude Haiku 4.5 and 36.9% for Gemini 2.5 Flash-Lite.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Haiku 4.5 | Gemini 2.5 Flash-Lite | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.3 | 36.4 |
| Released | 2025-10-15 | 2025-06-17 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 66K |
| Input $ / M tokens | $1 | $0.10 |
| Output $ / M tokens | $5 | $0.40 |
| Results tracked | 53 | 33 |
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 2.5 Flash-Lite: 38.0 (#167)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash-Lite |
|---|---|---|
| WeirdML | 45.4% | 35.2% |
| LMArena Coding | 1454 | 1373 |
| ALE-Bench | 653.48 | 325.9 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.5 (#50), Gemini 2.5 Flash-Lite: 27.8 (#89)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash-Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | 68.7% | 36.9% |
| Terminal-Bench | 35.5% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Gemini 2.5 Flash-Lite leads
Claude Haiku 4.5: 15.1 (#310), Gemini 2.5 Flash-Lite: 21.5 (#196)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1377 |
| DTBench | 73.6% | 62.8% |
| LMCA | 30.9% | 18.1% |
| Epoch Capabilities Index | 142.42 | 133.93 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | — | 40.5% |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.0 (#69), Gemini 2.5 Flash-Lite: 35.5 (#144)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash-Lite |
|---|---|---|
| Omni-MATH | 56.1% | 48% |
| LMArena Math | 1395 | 1373 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| 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 2.5 Flash-Lite: 32.1 (#206)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash-Lite |
|---|---|---|
| MMLU-Pro | 77.7% | 53.7% |
| Vectara Hallucination Rate | 9.8% | 3.3% |
| GPQA (HELM) | 60.5% | 30.9% |
| LMArena Expert | 1443 | 1373 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
Multimodal Gemini 2.5 Flash-Lite leads
Claude Haiku 4.5: 27.0 (#111), Gemini 2.5 Flash-Lite: 28.6 (#109)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Vision | — | 1198 |
| VPCT | — | 30% |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Too close to call
Claude Haiku 4.5: 50.1 (#124), Gemini 2.5 Flash-Lite: 49.5 (#129)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1376 | 1369 |
| LMArena Chinese | 1415 | 1404 |
| LMArena French | 1408 | 1388 |
| LMArena German | 1377 | 1390 |
| LMArena Japanese | 1339 | 1359 |
| LMArena Korean | 1346 | 1358 |
| LMArena Russian | 1380 | 1373 |
| LMArena Spanish | 1420 | 1396 |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.6 (#144), Gemini 2.5 Flash-Lite: 70.2 (#163)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash-Lite |
|---|---|---|
| IFEval | 80.1% | 81% |
| LMArena Instruction Following | 1414 | 1366 |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#86), Gemini 2.5 Flash-Lite: 33.3 (#257)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Longer Query | 1427 | 1373 |
| Fiction.LiveBench | — | 47.2% |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 58.1 (#119), Gemini 2.5 Flash-Lite: 57.0 (#130)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Text | 1396 | 1379 |
| LMArena Creative Writing | 1371 | 1366 |
| WildBench | 83.9% | 81.8% |
| LMArena Multi-Turn | 1409 | 1367 |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Gemini 2.5 Flash-Lite?
Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 11× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Which is cheaper, Claude Haiku 4.5 or Gemini 2.5 Flash-Lite?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Gemini 2.5 Flash-Lite better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 38.0 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and Gemini 2.5 Flash-Lite share?
29 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemini 2.5 Flash-Lite has 33.