Model comparison
Claude Haiku 4.5 vs Llama 3.2 3B
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 28.9 on the Noometry Index. Llama 3.2 3B costs 17× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
MetaSummary
- They share 15 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 8 categories and Llama 3.2 3B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Haiku 4.5 leads 57.9 to 24.7.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 68.7% for Claude Haiku 4.5 and 21.9% for Llama 3.2 3B.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 131K.
- Llama 3.2 3B has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Llama 3.2 3B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 39.5 | 28.9 |
| Released | 2025-10-15 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 64K | 118K |
| Input $ / M tokens | $1 | $0.05 |
| Output $ / M tokens | $5 | $0.33 |
| Results tracked | 53 | 18 |
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), Llama 3.2 3B: 27.6 (#319)
| Benchmark | Claude Haiku 4.5 | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1453 | 1098 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.6 (#52), Llama 3.2 3B: 20.1 (#143)
| Benchmark | Claude Haiku 4.5 | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 68.7% | 21.9% |
| BALROG | 31.2% | 10.1% |
| Terminal-Bench | 35.5% | — |
| DeepResearch Bench | 45.5% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Llama 3.2 3B leads
Claude Haiku 4.5: 15.1 (#320), Llama 3.2 3B: 21.0 (#228)
| Benchmark | Claude Haiku 4.5 | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1095 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Llama 3.2 3B: 32.4 (#214)
| Benchmark | Claude Haiku 4.5 | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1396 | 1126 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| 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), Llama 3.2 3B: 29.7 (#235)
| Benchmark | Claude Haiku 4.5 | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1442 | 1090 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Llama 3.2 3B: —
| Benchmark | Claude Haiku 4.5 | Llama 3.2 3B |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 49.9 (#129), Llama 3.2 3B: 26.2 (#281)
| Benchmark | Claude Haiku 4.5 | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1377 | 1019 |
| LMArena Chinese | 1417 | 1017 |
| LMArena German | 1375 | 1056 |
| LMArena Russian | 1381 | 949 |
| LMArena French | 1408 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.4 (#149), Llama 3.2 3B: 56.0 (#275)
| Benchmark | Claude Haiku 4.5 | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1414 | 1089 |
| IFEval | 80.1% | — |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#92), Llama 3.2 3B: 33.4 (#261)
| Benchmark | Claude Haiku 4.5 | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1427 | 1100 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Llama 3.2 3B: 24.7 (#307)
| Benchmark | Claude Haiku 4.5 | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1396 | 1110 |
| LMArena Creative Writing | 1372 | 1094 |
| LMArena Multi-Turn | 1409 | 1105 |
| EQ-Bench Creative Writing | — | 595 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Llama 3.2 3B?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 28.9 on the Noometry Index. Llama 3.2 3B costs 17× 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 Llama 3.2 3B?
Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Llama 3.2 3B better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 4.5 does, with 200K tokens against 131K.
How many benchmarks do Claude Haiku 4.5 and Llama 3.2 3B share?
15 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Llama 3.2 3B has 18.