Model comparison
Claude Haiku 4.5 vs Gemini 3.6 Flash
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 39.3 on the Noometry Index.
Last verified . 34 shared benchmarks.
GoogleSummary
- They share 34 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 1 category and Gemini 3.6 Flash in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.9 to 15.1.
- The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 89% for Gemini 3.6 Flash.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Haiku 4.5 | Gemini 3.6 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.3 | 54.1 |
| Released | 2025-10-15 | 2026-07-21 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 66K |
| Input $ / M tokens | $1 | $0.75 |
| Output $ / M tokens | $5 | $3.75 |
| Results tracked | 53 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
Claude Haiku 4.5: 43.9 (#71), Gemini 3.6 Flash: 49.6 (#45)
| Benchmark | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena WebDev | 1330 | 1536 |
| SciCode | 43.3% | 52.7% |
| WeirdML | 45.4% | 56.1% |
| LMArena Coding | 1454 | 1492 |
| ALE-Bench | 653.48 | 715.52 |
| DeepSWE | — | 46.7% |
| FrontierCode | — | 34.4% |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.5 (#50), Gemini 3.6 Flash: 32.4 (#56)
| Benchmark | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| APEX-Agents | — | 46.9% |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| GDP.pdf | — | 14% |
| Vending-Bench 2 | 458.89 | — |
Reasoning Gemini 3.6 Flash leads
Claude Haiku 4.5: 15.1 (#310), Gemini 3.6 Flash: 58.9 (#20)
| Benchmark | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| ARC-AGI-2 | 4% | 60.4% |
| NYT Connections (extended) | 14.3% | 89% |
| ARC-AGI-1 | 47.7% | 91.2% |
| CritPt | 0% | 10.6% |
| Chess Puzzles | 8% | 43% |
| LMArena Hard Prompts | 1420 | 1486 |
| DTBench | 73.6% | 95.5% |
| LMCA | 30.9% | 44.9% |
| Epoch Capabilities Index | 142.42 | 154.36 |
| Mystery Game Puzzles | — | 30% |
| ForecastBench | 61.4 | — |
Math Gemini 3.6 Flash leads
Claude Haiku 4.5: 43.0 (#69), Gemini 3.6 Flash: 57.0 (#33)
| Benchmark | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 94.2% |
| LMArena Math | 1395 | 1504 |
| FrontierMath (Tiers 1-3) | — | 58.9% |
| FrontierMath Tier 4 | — | 22% |
| MathArena Final-Answer Competitions | — | 70.8% |
| ProofBench | — | 36% |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Gemini 3.6 Flash leads
Claude Haiku 4.5: 37.6 (#146), Gemini 3.6 Flash: 67.8 (#7)
| Benchmark | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| GPQA Diamond | 71.2% | 94.1% |
| SimpleQA Verified | 13.2% | 66.2% |
| LMArena Expert | 1443 | 1489 |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Gemini 3.6 Flash leads
Claude Haiku 4.5: 27.0 (#111), Gemini 3.6 Flash: 38.7 (#55)
| Benchmark | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| Blueprint-Bench 2 | 0% | 31.2% |
| LMArena Document | 1420 | 1456 |
| LMArena Vision | — | 1297 |
| Furniture Assembly | — | 23.3% |
Multilingual Gemini 3.6 Flash leads
Claude Haiku 4.5: 50.1 (#124), Gemini 3.6 Flash: 56.8 (#17)
| Benchmark | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | 1376 | 1470 |
| LMArena Chinese | 1415 | 1530 |
| LMArena French | 1408 | 1501 |
| LMArena German | 1377 | 1478 |
| LMArena Japanese | 1339 | 1477 |
| LMArena Korean | 1346 | 1435 |
| LMArena Russian | 1380 | 1490 |
| LMArena Spanish | 1420 | 1477 |
Instruction Following Gemini 3.6 Flash leads
Claude Haiku 4.5: 71.6 (#144), Gemini 3.6 Flash: 77.2 (#27)
| Benchmark | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1414 | 1467 |
| IFEval | 80.1% | — |
Long Context Gemini 3.6 Flash leads
Claude Haiku 4.5: 43.6 (#86), Gemini 3.6 Flash: 45.1 (#47)
| Benchmark | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1427 | 1475 |
Writing & Preference Gemini 3.6 Flash leads
Claude Haiku 4.5: 58.1 (#119), Gemini 3.6 Flash: 68.3 (#26)
| Benchmark | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | 1396 | 1478 |
| LMArena Creative Writing | 1371 | 1464 |
| LMArena Multi-Turn | 1409 | 1481 |
| EQ-Bench Creative Writing | — | 1604 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Gemini 3.6 Flash?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 39.3 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or Gemini 3.6 Flash?
Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Gemini 3.6 Flash better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 43.9 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.6 Flash does, with 1.05M tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and Gemini 3.6 Flash share?
34 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemini 3.6 Flash has 46.