Model comparison
Claude 3 Haiku vs Nova Premier 1.0
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 25.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Summary
- They share 1 benchmark with published results for both. Claude 3 Haiku scores higher in 0 categories and Nova Premier 1.0 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Nova Premier 1.0 leads 33.8 to 9.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 34.2% for Claude 3 Haiku and 44.8% for Nova Premier 1.0.
Side by side
| Claude 3 Haiku | Nova Premier 1.0 | |
|---|---|---|
| Provider | Anthropic | Amazon |
| Noometry Index | 25.9 | 38.3 |
| Released | 2024-03-07 | 2025-04-30 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 10K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $12.50 |
| Results tracked | 37 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 3 Haiku: 26.4 (#325), Nova Premier 1.0: —
| Benchmark | Claude 3 Haiku | Nova Premier 1.0 |
|---|---|---|
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| LMArena Coding | 1199 | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Nova Premier 1.0 leads
Claude 3 Haiku: 16.3 (#307), Nova Premier 1.0: 23.0 (#185)
| Benchmark | Claude 3 Haiku | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 44.8% |
| LMArena Hard Prompts | 1174 | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Nova Premier 1.0 leads
Claude 3 Haiku: 9.8 (#319), Nova Premier 1.0: 33.8 (#199)
| Benchmark | Claude 3 Haiku | Nova Premier 1.0 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| Omni-MATH | — | 35% |
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |
Knowledge Nova Premier 1.0 leads
Claude 3 Haiku: 17.3 (#285), Nova Premier 1.0: 35.8 (#180)
| Benchmark | Claude 3 Haiku | Nova Premier 1.0 |
|---|---|---|
| GPQA Diamond | 36.3% | — |
| MMLU-Pro | — | 72.6% |
| Confabulations | 34.2% | — |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1148 | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Nova Premier 1.0: —
| Benchmark | Claude 3 Haiku | Nova Premier 1.0 |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Not comparable
Claude 3 Haiku: 36.0 (#243), Nova Premier 1.0: —
| Benchmark | Claude 3 Haiku | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1178 | — |
| LMArena Chinese | 1155 | — |
| LMArena French | 1195 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |
| LMArena Russian | 1204 | — |
| LMArena Spanish | 1166 | — |
Instruction Following Nova Premier 1.0 leads
Claude 3 Haiku: 61.3 (#247), Nova Premier 1.0: 66.8 (#204)
| Benchmark | Claude 3 Haiku | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1173 | — |
Long Context Not comparable
Claude 3 Haiku: 36.1 (#237), Nova Premier 1.0: —
| Benchmark | Claude 3 Haiku | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1190 | — |
Writing & Preference Nova Premier 1.0 leads
Claude 3 Haiku: 29.7 (#291), Nova Premier 1.0: 51.0 (#178)
| Benchmark | Claude 3 Haiku | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1195 | — |
| LMArena Creative Writing | 1157 | — |
| EQ-Bench Creative Writing | 717 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is Claude 3 Haiku better than Nova Premier 1.0?
Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 25.9 on the Noometry Index.
How many benchmarks do Claude 3 Haiku and Nova Premier 1.0 share?
1 benchmark has published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Nova Premier 1.0 has 6.