Model comparison
Claude Haiku 4.5 vs Gemini 2.0 Flash (Feb 2025)
Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 34.8 on the Noometry Index.
Last verified . 31 shared benchmarks.
GoogleSummary
- They share 31 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Gemini 2.0 Flash (Feb 2025) in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Haiku 4.5 leads 43.9 to 28.2.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 66.6% for Claude Haiku 4.5 and 13.5% for Gemini 2.0 Flash (Feb 2025).
Side by side
| Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.3 | 34.8 |
| Released | 2025-10-15 | 2024-12-06 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 54 |
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 (Feb 2025): 28.2 (#308)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 66.6% | 13.5% |
| WeirdML | 45.4% | 25.8% |
| LMArena Coding | 1454 | 1351 |
| Aider Polyglot | — | 38.2% |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| BigCodeBench Instruct | — | 45.9% |
| LiveBench Coding | — | 63.4% |
| BigCodeBench Complete | — | 59.9% |
| CadEval | — | 30% |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.5 (#50), Gemini 2.0 Flash (Feb 2025): 28.0 (#85)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| TheAgentCompany | — | 11.4% |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Too close to call
Claude Haiku 4.5: 15.1 (#310), Gemini 2.0 Flash (Feb 2025): 15.2 (#308)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| ARC-AGI-2 | 4% | 1.3% |
| LMArena Hard Prompts | 1420 | 1346 |
| DTBench | 73.6% | 63.2% |
| Epoch Capabilities Index | 142.42 | 135.36 |
| SimpleBench | — | 31.1% |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| EnigmaEval | — | 1.1% |
| LiveBench Reasoning | — | 78.2% |
| LiveBench Data Analysis | — | 69.4% |
| LMCA | 30.9% | — |
| ForecastBench | 61.4 | — |
| LiveBench | — | 66.9% |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.0 (#69), Gemini 2.0 Flash (Feb 2025): 36.1 (#127)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 57.8% |
| Omni-MATH | 56.1% | 45.9% |
| LMArena Math | 1395 | 1351 |
| MATH Level 5 | 96.4% | 82.2% |
| FrontierMath (Feb 2025 set) | 5.9% | 1.7% |
| LiveBench Math | — | 75.8% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.6 (#146), Gemini 2.0 Flash (Feb 2025): 32.0 (#207)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| GPQA Diamond | 71.2% | 64.1% |
| MMLU-Pro | 77.7% | 73.7% |
| GPQA (HELM) | 60.5% | 55.6% |
| LMArena Expert | 1443 | 1340 |
| Humanity's Last Exam | — | 6.6% |
| SimpleQA Verified | 13.2% | — |
| Confabulations | — | 12.4% |
| Vectara Hallucination Rate | 9.8% | — |
| MMLU | — | 79.7% |
Multimodal Gemini 2.0 Flash (Feb 2025) leads
Claude Haiku 4.5: 27.0 (#111), Gemini 2.0 Flash (Feb 2025): 35.9 (#74)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Vision | — | 1158 |
| GeoBench | — | 77% |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 50.1 (#124), Gemini 2.0 Flash (Feb 2025): 47.6 (#144)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Non-English | 1376 | 1342 |
| LMArena Chinese | 1415 | 1373 |
| LMArena French | 1408 | 1390 |
| LMArena German | 1377 | 1354 |
| LMArena Japanese | 1339 | 1293 |
| LMArena Korean | 1346 | 1314 |
| LMArena Russian | 1380 | 1351 |
| LMArena Spanish | 1420 | 1363 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Claude Haiku 4.5: 71.6 (#144), Gemini 2.0 Flash (Feb 2025): 74.6 (#91)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| IFEval | 80.1% | 84.1% |
| LMArena Instruction Following | 1414 | 1336 |
| LiveBench Instruction Following | — | 85.8% |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#86), Gemini 2.0 Flash (Feb 2025): 38.1 (#198)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Longer Query | 1427 | 1345 |
| Fiction.LiveBench | — | 61.1% |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 58.1 (#119), Gemini 2.0 Flash (Feb 2025): 49.8 (#184)
| Benchmark | Claude Haiku 4.5 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Text | 1396 | 1354 |
| LMArena Creative Writing | 1371 | 1340 |
| WildBench | 83.9% | 80% |
| LMArena Multi-Turn | 1409 | 1350 |
| Short-Story Creative Writing | — | 73.8% |
| EQ-Bench Creative Writing | — | 1128 |
| EQ-Bench 4 | 1064 | — |
| LiveBench Language | — | 51.3% |
Frequently asked questions
Is Claude Haiku 4.5 better than Gemini 2.0 Flash (Feb 2025)?
Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 34.8 on the Noometry Index.
Is Claude Haiku 4.5 or Gemini 2.0 Flash (Feb 2025) better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 28.2 in the Noometry coding category.
How many benchmarks do Claude Haiku 4.5 and Gemini 2.0 Flash (Feb 2025) share?
31 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemini 2.0 Flash (Feb 2025) has 54.