Model comparison
GPT-4.1 nano vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 27.9 on the Noometry Index. GPT-4.1 nano costs 3.0× less per token, which makes it the better buy when Solar Pro4's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
UpstageSummary
- They share 14 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Solar Pro4 leads 28.5 to 8.5.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 524K.
Side by side
| GPT-4.1 nano | Solar Pro4 | |
|---|---|---|
| Provider | OpenAI | Upstage |
| Noometry Index | 27.9 | 42.1 |
| Released | 2025-04-14 | 2026-08-06 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 524K |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.10 | $0.30 |
| Output $ / M tokens | $0.40 | $1.20 |
| Results tracked | 38 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
GPT-4.1 nano: 24.1 (#330), Solar Pro4: 40.1 (#149)
| Benchmark | GPT-4.1 nano | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1306 | 1437 |
| Aider Polyglot | 8.9% | — |
| LMArena WebDev | — | 1371 |
| SciCode | 25.9% | — |
| WeirdML | 19% | — |
Agentic & Tool Use Not comparable
GPT-4.1 nano: 26.5 (#104), Solar Pro4: —
| Benchmark | GPT-4.1 nano | Solar Pro4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | — |
Reasoning Solar Pro4 leads
GPT-4.1 nano: 8.5 (#349), Solar Pro4: 28.5 (#104)
| Benchmark | GPT-4.1 nano | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1286 | 1399 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 33.3% | — |
| ARC-AGI-1 | 0% | — |
| CritPt | 0% | — |
| DTBench | 52.5% | — |
| LMCA | 5.5% | — |
| Epoch Capabilities Index | 129.62 | — |
Math Solar Pro4 leads
GPT-4.1 nano: 26.9 (#252), Solar Pro4: 38.8 (#128)
| Benchmark | GPT-4.1 nano | Solar Pro4 |
|---|---|---|
| LMArena Math | 1274 | 1416 |
| OTIS Mock AIME 2024-2025 | 28.9% | — |
| Omni-MATH | 36.7% | — |
| MATH Level 5 | 70% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Solar Pro4 leads
GPT-4.1 nano: 21.8 (#273), Solar Pro4: 39.8 (#129)
| Benchmark | GPT-4.1 nano | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1272 | 1427 |
| GPQA Diamond | 48.9% | — |
| SimpleQA Verified | 6% | — |
| MMLU-Pro | 55% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
GPT-4.1 nano: 29.2 (#113), Solar Pro4: —
| Benchmark | GPT-4.1 nano | Solar Pro4 |
|---|---|---|
| LMArena Vision | 1063 | — |
Multilingual Solar Pro4 leads
GPT-4.1 nano: 41.6 (#205), Solar Pro4: 48.7 (#139)
| Benchmark | GPT-4.1 nano | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1260 | 1361 |
| LMArena Chinese | 1270 | 1415 |
| LMArena German | 1288 | 1364 |
| LMArena Japanese | 1198 | 1309 |
| LMArena Russian | 1261 | 1360 |
| LMArena French | — | 1397 |
| LMArena Korean | — | 1382 |
| LMArena Spanish | — | 1401 |
Instruction Following Solar Pro4 leads
GPT-4.1 nano: 67.8 (#193), Solar Pro4: 72.7 (#132)
| Benchmark | GPT-4.1 nano | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1267 | 1377 |
| IFEval | 84.3% | — |
Long Context Solar Pro4 leads
GPT-4.1 nano: 23.7 (#296), Solar Pro4: 42.1 (#130)
| Benchmark | GPT-4.1 nano | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1283 | 1381 |
| Fiction.LiveBench | 25% | — |
Writing & Preference Solar Pro4 leads
GPT-4.1 nano: 40.5 (#243), Solar Pro4: 56.5 (#138)
| Benchmark | GPT-4.1 nano | Solar Pro4 |
|---|---|---|
| LMArena Text | 1285 | 1386 |
| LMArena Creative Writing | 1260 | 1316 |
| LMArena Multi-Turn | 1277 | 1385 |
| EQ-Bench Creative Writing | 946 | — |
| WildBench | 81.2% | — |
Frequently asked questions
Is GPT-4.1 nano better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 27.9 on the Noometry Index. GPT-4.1 nano costs 3.0× less per token, which makes it the better buy when Solar Pro4's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 nano or Solar Pro4?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.
Is GPT-4.1 nano or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 524K.
How many benchmarks do GPT-4.1 nano and Solar Pro4 share?
14 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Solar Pro4 has 18.