# Claude Haiku 4.5 vs Solar Pro4

> Solar Pro4 is the stronger model overall, scoring 42.1 to 39.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-4-5-vs-solar-pro4
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 5 categories and Solar Pro4 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Solar Pro4 leads 28.5 to 15.1.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Solar Pro4 accepts more context: 524K tokens versus 200K.

## Snapshot

| | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| Provider | Anthropic | Upstage |
| Noometry Index | 39.5 | 42.1 |
| Rank | 165 | 121 |
| Context | 200K | 524K |
| Input $/M | $1 | $0.30 |
| Output $/M | $5 | $1.20 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Haiku 4.5: 44.0 (#78)
- Solar Pro4: 40.1 (#149)

| Benchmark | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| LMArena WebDev | 1330 | 1371 |
| LMArena Coding | 1453 | 1437 |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.6 (#52)
- Solar Pro4: —

| Benchmark | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| 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

- Claude Haiku 4.5: 15.1 (#320)
- Solar Pro4: 28.5 (#104)

| Benchmark | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1399 |
| 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: 44.9 (#78)
- Solar Pro4: 38.8 (#128)

| Benchmark | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| LMArena Math | 1396 | 1416 |
| 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: 37.7 (#153)
- Solar Pro4: 39.8 (#129)

| Benchmark | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1442 | 1427 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |

## Multimodal

- Claude Haiku 4.5: 26.8 (#118)
- Solar Pro4: —

| Benchmark | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |

## Multilingual

- Claude Haiku 4.5: 49.9 (#129)
- Solar Pro4: 48.7 (#139)

| Benchmark | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1377 | 1361 |
| LMArena Chinese | 1417 | 1415 |
| LMArena French | 1408 | 1397 |
| LMArena German | 1375 | 1364 |
| LMArena Japanese | 1339 | 1309 |
| LMArena Korean | 1347 | 1382 |
| LMArena Russian | 1381 | 1360 |
| LMArena Spanish | 1420 | 1401 |

## Instruction Following

- Claude Haiku 4.5: 71.4 (#149)
- Solar Pro4: 72.7 (#132)

| Benchmark | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1414 | 1377 |
| IFEval | 80.1% | — |

## Long Context

- Claude Haiku 4.5: 43.6 (#92)
- Solar Pro4: 42.1 (#130)

| Benchmark | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1427 | 1381 |

## Writing & Preference

- Claude Haiku 4.5: 57.9 (#123)
- Solar Pro4: 56.5 (#138)

| Benchmark | Claude Haiku 4.5 | Solar Pro4 |
|---|---|---|
| LMArena Text | 1396 | 1386 |
| LMArena Creative Writing | 1372 | 1316 |
| LMArena Multi-Turn | 1409 | 1385 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |

## FAQ

### Is Claude Haiku 4.5 better than Solar Pro4?

Solar Pro4 is the stronger model overall, scoring 42.1 to 39.5 on the Noometry Index.

### Which is cheaper, Claude Haiku 4.5 or Solar Pro4?

Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.

### Is Claude Haiku 4.5 or Solar Pro4 better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 40.1 in the Noometry coding category.

### Which has the bigger context window?

Solar Pro4 does, with 524K tokens against 200K.

### How many benchmarks do Claude Haiku 4.5 and Solar Pro4 share?

18 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Solar Pro4 has 18.