Model comparison
Claude Haiku 4.5 vs Llama 3.1 Nemotron Ultra 253b v1
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 36.7 on the Noometry Index.
Last verified . 11 shared benchmarks.
NVIDIASummary
- They share 11 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Llama 3.1 Nemotron Ultra 253b v1 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Haiku 4.5 leads 33.6 to 15.7.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 68.7% for Claude Haiku 4.5 and 10% for Llama 3.1 Nemotron Ultra 253b v1.
- Llama 3.1 Nemotron Ultra 253b v1 has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 | |
|---|---|---|
| Provider | Anthropic | NVIDIA |
| Noometry Index | 39.5 | 36.7 |
| Released | 2025-10-15 | — |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 11 |
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 3.1 Nemotron Ultra 253b v1: 38.4 (#177)
| Benchmark | Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Coding | 1453 | 1312 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.6 (#52), Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149)
| Benchmark | Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 68.7% | 10% |
| Terminal-Bench | 35.5% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Llama 3.1 Nemotron Ultra 253b v1 leads
Claude Haiku 4.5: 15.1 (#320), Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134)
| Benchmark | Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1316 |
| 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 3.1 Nemotron Ultra 253b v1: 37.5 (#152)
| Benchmark | Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Math | 1396 | 1360 |
| 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 Not comparable
Claude Haiku 4.5: 37.7 (#153), Llama 3.1 Nemotron Ultra 253b v1: —
| Benchmark | Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
| LMArena Expert | 1442 | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Llama 3.1 Nemotron Ultra 253b v1: —
| Benchmark | Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 49.9 (#129), Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187)
| Benchmark | Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Non-English | 1377 | 1282 |
| LMArena Russian | 1381 | 1284 |
| LMArena Chinese | 1417 | — |
| LMArena French | 1408 | — |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.4 (#149), Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178)
| Benchmark | Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Instruction Following | 1414 | 1308 |
| IFEval | 80.1% | — |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#92), Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177)
| Benchmark | Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Longer Query | 1427 | 1299 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175)
| Benchmark | Claude Haiku 4.5 | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Text | 1396 | 1320 |
| LMArena Creative Writing | 1372 | 1314 |
| LMArena Multi-Turn | 1409 | 1317 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Llama 3.1 Nemotron Ultra 253b v1?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 36.7 on the Noometry Index.
Is Claude Haiku 4.5 or Llama 3.1 Nemotron Ultra 253b v1 better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 38.4 in the Noometry coding category.
How many benchmarks do Claude Haiku 4.5 and Llama 3.1 Nemotron Ultra 253b v1 share?
11 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Llama 3.1 Nemotron Ultra 253b v1 has 11.