Model comparison
Claude Haiku 4.5 vs Gemma 2 27B
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 29.4 on the Noometry Index. Gemma 2 27B costs 3.1× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Gemma 2 27B 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 10.7.
- The biggest single-benchmark swing is MATH Level 5: 96.4% for Claude Haiku 4.5 and 27.9% for Gemma 2 27B.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 8K.
- Gemma 2 27B has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Gemma 2 27B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.5 | 29.4 |
| Released | 2025-10-15 | 2024-06-24 |
| Weights | Proprietary | Open |
| Context window | 200K | 8K |
| Max output | 64K | 2K |
| Input $ / M tokens | $1 | $0.65 |
| Output $ / M tokens | $5 | $0.65 |
| Results tracked | 53 | 34 |
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 27B: 34.1 (#246)
| Benchmark | Claude Haiku 4.5 | Gemma 2 27B |
|---|---|---|
| LMArena Coding | 1453 | 1211 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| BigCodeBench Instruct | — | 42.8% |
| LiveBench Coding | — | 36% |
| BigCodeBench Complete | — | 52.5% |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Gemma 2 27B: —
| Benchmark | Claude Haiku 4.5 | Gemma 2 27B |
|---|---|---|
| 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 27B: 15.3 (#315)
| Benchmark | Claude Haiku 4.5 | Gemma 2 27B |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1198 |
| DTBench | 73.6% | 48% |
| LMCA | 30.9% | 7.1% |
| Epoch Capabilities Index | 142.41 | 122.08 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LiveBench Reasoning | — | 28.1% |
| LiveBench Data Analysis | — | 47.9% |
| ForecastBench | 61.4 | — |
| LiveBench | — | 38.2% |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Gemma 2 27B: 10.7 (#311)
| Benchmark | Claude Haiku 4.5 | Gemma 2 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 1.4% |
| LMArena Math | 1396 | 1212 |
| MATH Level 5 | 96.4% | 27.9% |
| Omni-MATH | 56.1% | — |
| LiveBench Math | — | 26.5% |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.7 (#153), Gemma 2 27B: 19.0 (#280)
| Benchmark | Claude Haiku 4.5 | Gemma 2 27B |
|---|---|---|
| GPQA Diamond | 71.2% | 36.5% |
| LMArena Expert | 1442 | 1172 |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | — | 27.1% |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
| MMLU | — | 75.7% |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Gemma 2 27B: —
| Benchmark | Claude Haiku 4.5 | Gemma 2 27B |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 49.9 (#129), Gemma 2 27B: 38.6 (#226)
| Benchmark | Claude Haiku 4.5 | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | 1377 | 1217 |
| LMArena Chinese | 1417 | 1221 |
| LMArena French | 1408 | 1247 |
| LMArena German | 1375 | 1209 |
| LMArena Japanese | 1339 | 1175 |
| LMArena Korean | 1347 | 1174 |
| LMArena Russian | 1381 | 1234 |
| LMArena Spanish | 1420 | 1228 |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.4 (#149), Gemma 2 27B: 60.5 (#249)
| Benchmark | Claude Haiku 4.5 | Gemma 2 27B |
|---|---|---|
| LMArena Instruction Following | 1414 | 1206 |
| LiveBench Instruction Following | — | 58.1% |
| IFEval | 80.1% | — |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#92), Gemma 2 27B: 37.3 (#218)
| Benchmark | Claude Haiku 4.5 | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | 1427 | 1231 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Gemma 2 27B: 44.2 (#225)
| Benchmark | Claude Haiku 4.5 | Gemma 2 27B |
|---|---|---|
| LMArena Text | 1396 | 1231 |
| LMArena Creative Writing | 1372 | 1241 |
| LMArena Multi-Turn | 1409 | 1224 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
| LiveBench Language | — | 32.6% |
Frequently asked questions
Is Claude Haiku 4.5 better than Gemma 2 27B?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 29.4 on the Noometry Index. Gemma 2 27B costs 3.1× 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 Gemma 2 27B?
Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Gemma 2 27B better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 4.5 does, with 200K tokens against 8K.
How many benchmarks do Claude Haiku 4.5 and Gemma 2 27B share?
23 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemma 2 27B has 34.