Model comparison
Claude Haiku 4.5 vs Gemini 2.5 Flash
Claude Haiku 4.5 and Gemini 2.5 Flash score almost the same on the Noometry Index (39.5 vs 39.3), so choose on price, context window or the category you care about most.
Last verified . 40 shared benchmarks.
GoogleSummary
- They share 40 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 5 categories and Gemini 2.5 Flash in 5 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Gemini 2.5 Flash leads 41.8 to 26.8.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 66.6% for Claude Haiku 4.5 and 28.7% for Gemini 2.5 Flash.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Haiku 4.5 | Gemini 2.5 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.5 | 39.3 |
| Released | 2025-10-15 | 2025-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 66K |
| Input $ / M tokens | $1 | $0.30 |
| Output $ / M tokens | $5 | $2.50 |
| 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: 44.0 (#78), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| SWE-bench Verified (bash only) | 66.6% | 28.7% |
| WeirdML | 45.4% | 41.9% |
| LMArena Coding | 1453 | 1424 |
| ALE-Bench | 653.48 | 661.88 |
| Aider Polyglot | — | 55.1% |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.6 (#52), Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| Terminal-Bench | 35.5% | 17.1% |
| Berkeley Function Calling Leaderboard | 68.7% | 56.2% |
| BALROG | 31.2% | 33.5% |
| Vending-Bench 2 | 458.89 | 548.84 |
| TheAgentCompany | — | 41.1% |
| DeepResearch Bench | 45.5% | — |
| ExploitBench | 13.7% | — |
Reasoning Gemini 2.5 Flash leads
Claude Haiku 4.5: 15.1 (#320), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| ARC-AGI-2 | 4% | 2.5% |
| ARC-AGI-1 | 47.7% | 33.3% |
| CritPt | 0% | 1.1% |
| LMArena Hard Prompts | 1420 | 1422 |
| DTBench | 73.6% | 76.5% |
| LMCA | 30.9% | 27.5% |
| Epoch Capabilities Index | 142.41 | 143.03 |
| ForecastBench | 61.4 | 60.6 |
| SimpleBench | — | 41.2% |
| Kagi LLM Benchmark | — | 56.8% |
| NYT Connections (extended) | 14.3% | — |
| Chess Puzzles | 8% | — |
| EnigmaEval | — | 2.7% |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 73.1% |
| Omni-MATH | 56.1% | 38.5% |
| LMArena Math | 1396 | 1415 |
| FrontierMath (Feb 2025 set) | 5.9% | 4.8% |
| FrontierMath Tier 4 (v1) | 2.1% | 4.2% |
| MATH Level 5 | 96.4% | — |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.7 (#153), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| MMLU-Pro | 77.7% | 63.9% |
| Vectara Hallucination Rate | 9.8% | 7.8% |
| GPQA (HELM) | 60.5% | 39% |
| LMArena Expert | 1442 | 1426 |
| GPQA Diamond | 71.2% | — |
| Humanity's Last Exam | — | 12.1% |
| SimpleQA Verified | 13.2% | — |
| Confabulations | — | 16.8% |
Multimodal Gemini 2.5 Flash leads
Claude Haiku 4.5: 26.8 (#118), Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | — | 1253 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
| SpatialViz-Bench | — | 36.9% |
Multilingual Gemini 2.5 Flash leads
Claude Haiku 4.5: 49.9 (#129), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1377 | 1409 |
| LMArena Chinese | 1417 | 1450 |
| LMArena French | 1408 | 1433 |
| LMArena German | 1375 | 1418 |
| LMArena Japanese | 1339 | 1405 |
| LMArena Korean | 1347 | 1385 |
| LMArena Russian | 1381 | 1415 |
| LMArena Spanish | 1420 | 1421 |
Instruction Following Gemini 2.5 Flash leads
Claude Haiku 4.5: 71.4 (#149), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| IFEval | 80.1% | 89.8% |
| LMArena Instruction Following | 1414 | 1405 |
Long Context Gemini 2.5 Flash leads
Claude Haiku 4.5: 43.6 (#92), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1427 | 1419 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1396 | 1417 |
| LMArena Creative Writing | 1372 | 1400 |
| WildBench | 83.9% | 81.7% |
| LMArena Multi-Turn | 1409 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| EQ-Bench Creative Writing | — | 1137 |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Gemini 2.5 Flash?
Claude Haiku 4.5 and Gemini 2.5 Flash score almost the same on the Noometry Index (39.5 vs 39.3), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Haiku 4.5 or Gemini 2.5 Flash?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Gemini 2.5 Flash better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and Gemini 2.5 Flash share?
40 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemini 2.5 Flash has 54.