Model comparison
Claude Haiku 4.5 vs Gemma 2 9B
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 25.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Gemma 2 9B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 4.5 leads 44.9 to 9.9.
- The biggest single-benchmark swing is MATH Level 5: 96.4% for Claude Haiku 4.5 and 21% for Gemma 2 9B.
- Gemma 2 9B has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Gemma 2 9B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.5 | 25.9 |
| Released | 2025-10-15 | 2024-06-24 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 35 |
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), Gemma 2 9B: 29.4 (#304)
| Benchmark | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| LMArena Coding | 1453 | 1173 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| BigCodeBench Instruct | — | 34.7% |
| LiveBench Coding | — | 22.5% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Gemma 2 9B: —
| Benchmark | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| 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 Too close to call
Claude Haiku 4.5: 15.1 (#320), Gemma 2 9B: 15.9 (#309)
| Benchmark | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1171 |
| Epoch Capabilities Index | 142.41 | 119.83 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LiveBench Reasoning | — | 15.2% |
| DTBench | 73.6% | — |
| LiveBench Data Analysis | — | 36.4% |
| LMCA | 30.9% | — |
| ForecastBench | 61.4 | — |
| LiveBench | — | 28.7% |
| PIQA | — | 83.7% |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Gemma 2 9B: 9.9 (#318)
| Benchmark | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 0.6% |
| LMArena Math | 1396 | 1183 |
| MATH Level 5 | 96.4% | 21% |
| Omni-MATH | 56.1% | — |
| LiveBench Math | — | 19.8% |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 84.9% |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.7 (#153), Gemma 2 9B: 9.7 (#305)
| Benchmark | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| GPQA Diamond | 71.2% | 27.5% |
| LMArena Expert | 1442 | 1147 |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
| BoolQ | — | 85.7% |
| MMLU | — | 72.1% |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Gemma 2 9B: —
| Benchmark | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 49.9 (#129), Gemma 2 9B: 36.6 (#238)
| Benchmark | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| LMArena Non-English | 1377 | 1188 |
| LMArena Chinese | 1417 | 1185 |
| LMArena French | 1408 | 1190 |
| LMArena German | 1375 | 1186 |
| LMArena Japanese | 1339 | 1144 |
| LMArena Korean | 1347 | 1137 |
| LMArena Russian | 1381 | 1200 |
| LMArena Spanish | 1420 | 1200 |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.4 (#149), Gemma 2 9B: 57.6 (#269)
| Benchmark | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| LMArena Instruction Following | 1414 | 1178 |
| LiveBench Instruction Following | — | 52.6% |
| IFEval | 80.1% | — |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#92), Gemma 2 9B: 36.3 (#233)
| Benchmark | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | 1427 | 1197 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Gemma 2 9B: 32.1 (#281)
| Benchmark | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| LMArena Text | 1396 | 1207 |
| LMArena Creative Writing | 1372 | 1206 |
| LMArena Multi-Turn | 1409 | 1193 |
| EQ-Bench Creative Writing | — | 841 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
| LiveBench Language | — | 25.5% |
Frequently asked questions
Is Claude Haiku 4.5 better than Gemma 2 9B?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 25.9 on the Noometry Index.
Is Claude Haiku 4.5 or Gemma 2 9B better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 29.4 in the Noometry coding category.
How many benchmarks do Claude Haiku 4.5 and Gemma 2 9B share?
21 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemma 2 9B has 35.