# Claude 3 Haiku vs Nova 2 Lite

> Nova 2 Lite is the stronger model overall, scoring 39.7 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-nova-2-lite
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Nova 2 Lite in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Nova 2 Lite leads 37.5 to 9.8.

## Snapshot

| | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| Provider | Anthropic | Amazon |
| Noometry Index | 25.9 | 39.7 |
| Rank | 340 | 161 |
| Context | — | 1M |
| Input $/M | — | $0.30 |
| Output $/M | — | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- Nova 2 Lite: 40.7 (#134)

| Benchmark | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1199 | 1385 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- Nova 2 Lite: 24.1 (#121)

| Benchmark | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- Nova 2 Lite: 27.5 (#118)

| Benchmark | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1364 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.8 (#319)
- Nova 2 Lite: 37.5 (#156)

| Benchmark | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1188 | 1359 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- Nova 2 Lite: 43.0 (#94)

| Benchmark | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1148 | 1358 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- Nova 2 Lite: —

| Benchmark | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- Nova 2 Lite: 47.1 (#153)

| Benchmark | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1178 | 1337 |
| LMArena Chinese | 1155 | 1364 |
| LMArena French | 1195 | 1381 |
| LMArena German | 1174 | 1343 |
| LMArena Japanese | 1102 | 1271 |
| LMArena Korean | 1109 | 1284 |
| LMArena Russian | 1204 | 1343 |
| LMArena Spanish | 1166 | 1373 |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- Nova 2 Lite: 70.5 (#161)

| Benchmark | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1173 | 1335 |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- Nova 2 Lite: 40.6 (#150)

| Benchmark | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1190 | 1335 |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- Nova 2 Lite: 53.9 (#154)

| Benchmark | Claude 3 Haiku | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1195 | 1362 |
| LMArena Creative Writing | 1157 | 1291 |
| LMArena Multi-Turn | 1190 | 1338 |
| EQ-Bench Creative Writing | 717 | — |

## FAQ

### Is Claude 3 Haiku better than Nova 2 Lite?

Nova 2 Lite is the stronger model overall, scoring 39.7 to 25.9 on the Noometry Index.

### Is Claude 3 Haiku or Nova 2 Lite better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 26.4 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Nova 2 Lite share?

17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Nova 2 Lite has 19.