Model comparison
Claude 3 Haiku vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 25.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
UpstageSummary
- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Solar Pro4 leads 38.8 to 9.8.
Side by side
| Claude 3 Haiku | Solar Pro4 | |
|---|---|---|
| Provider | Anthropic | Upstage |
| Noometry Index | 25.9 | 42.1 |
| Released | 2024-03-07 | 2026-08-06 |
| Weights | Proprietary | Proprietary |
| Context window | — | 524K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 37 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Claude 3 Haiku: 26.4 (#325), Solar Pro4: 40.1 (#149)
| Benchmark | Claude 3 Haiku | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1199 | 1437 |
| LMArena WebDev | — | 1371 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Solar Pro4 leads
Claude 3 Haiku: 16.3 (#307), Solar Pro4: 28.5 (#104)
| Benchmark | Claude 3 Haiku | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1399 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Solar Pro4 leads
Claude 3 Haiku: 9.8 (#319), Solar Pro4: 38.8 (#128)
| Benchmark | Claude 3 Haiku | Solar Pro4 |
|---|---|---|
| LMArena Math | 1188 | 1416 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge Solar Pro4 leads
Claude 3 Haiku: 17.3 (#285), Solar Pro4: 39.8 (#129)
| Benchmark | Claude 3 Haiku | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1148 | 1427 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Solar Pro4: —
| Benchmark | Claude 3 Haiku | Solar Pro4 |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Solar Pro4 leads
Claude 3 Haiku: 36.0 (#243), Solar Pro4: 48.7 (#139)
| Benchmark | Claude 3 Haiku | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1178 | 1361 |
| LMArena Chinese | 1155 | 1415 |
| LMArena French | 1195 | 1397 |
| LMArena German | 1174 | 1364 |
| LMArena Japanese | 1102 | 1309 |
| LMArena Korean | 1109 | 1382 |
| LMArena Russian | 1204 | 1360 |
| LMArena Spanish | 1166 | 1401 |
Instruction Following Solar Pro4 leads
Claude 3 Haiku: 61.3 (#247), Solar Pro4: 72.7 (#132)
| Benchmark | Claude 3 Haiku | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1173 | 1377 |
Long Context Solar Pro4 leads
Claude 3 Haiku: 36.1 (#237), Solar Pro4: 42.1 (#130)
| Benchmark | Claude 3 Haiku | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1190 | 1381 |
Writing & Preference Solar Pro4 leads
Claude 3 Haiku: 29.7 (#291), Solar Pro4: 56.5 (#138)
| Benchmark | Claude 3 Haiku | Solar Pro4 |
|---|---|---|
| LMArena Text | 1195 | 1386 |
| LMArena Creative Writing | 1157 | 1316 |
| LMArena Multi-Turn | 1190 | 1385 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Solar Pro4 share?
17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Solar Pro4 has 18.