Model comparison
GPT-5 Mini vs Solar Pro4
GPT-5 Mini and Solar Pro4 score almost the same on the Noometry Index (41.8 vs 42.1), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
UpstageSummary
- They share 17 benchmarks with published results for both. GPT-5 Mini scores higher in 5 categories and Solar Pro4 in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.7 to 38.8.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- Solar Pro4 accepts more context: 524K tokens versus 400K.
Side by side
| GPT-5 Mini | Solar Pro4 | |
|---|---|---|
| Provider | OpenAI | Upstage |
| Noometry Index | 41.8 | 42.1 |
| Released | 2025-08-07 | 2026-08-06 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 524K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.25 | $0.30 |
| Output $ / M tokens | $2 | $1.20 |
| Results tracked | 60 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5 Mini: 40.1 (#146), Solar Pro4: 40.1 (#149)
| Benchmark | GPT-5 Mini | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1406 | 1437 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| LMArena WebDev | — | 1371 |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| WeirdML | 52.7% | — |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Not comparable
GPT-5 Mini: 31.1 (#70), Solar Pro4: —
| Benchmark | GPT-5 Mini | Solar Pro4 |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning Solar Pro4 leads
GPT-5 Mini: 23.9 (#168), Solar Pro4: 28.5 (#104)
| Benchmark | GPT-5 Mini | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1380 | 1399 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
| Epoch Capabilities Index | 145.52 | — |
| ForecastBench | 61 | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), Solar Pro4: 38.8 (#128)
| Benchmark | GPT-5 Mini | Solar Pro4 |
|---|---|---|
| LMArena Math | 1378 | 1416 |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), Solar Pro4: 39.8 (#129)
| Benchmark | GPT-5 Mini | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1379 | 1427 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), Solar Pro4: —
| Benchmark | GPT-5 Mini | Solar Pro4 |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual Too close to call
GPT-5 Mini: 48.9 (#137), Solar Pro4: 48.7 (#139)
| Benchmark | GPT-5 Mini | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1363 | 1361 |
| LMArena Chinese | 1385 | 1415 |
| LMArena French | 1386 | 1397 |
| LMArena German | 1366 | 1364 |
| LMArena Japanese | 1341 | 1309 |
| LMArena Korean | 1308 | 1382 |
| LMArena Russian | 1362 | 1360 |
| LMArena Spanish | 1355 | 1401 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), Solar Pro4: 72.7 (#132)
| Benchmark | GPT-5 Mini | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1377 |
| IFEval | 92.7% | — |
Long Context Too close to call
GPT-5 Mini: 41.9 (#132), Solar Pro4: 42.1 (#130)
| Benchmark | GPT-5 Mini | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1355 | 1381 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference Solar Pro4 leads
GPT-5 Mini: 55.2 (#148), Solar Pro4: 56.5 (#138)
| Benchmark | GPT-5 Mini | Solar Pro4 |
|---|---|---|
| LMArena Text | 1373 | 1386 |
| LMArena Creative Writing | 1325 | 1316 |
| LMArena Multi-Turn | 1363 | 1385 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than Solar Pro4?
GPT-5 Mini and Solar Pro4 score almost the same on the Noometry Index (41.8 vs 42.1), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5 Mini or Solar Pro4?
Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Is GPT-5 Mini or Solar Pro4 better for coding?
They score almost the same on coding (40.1 vs 40.1); test both on your own repository before choosing.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 400K.
How many benchmarks do GPT-5 Mini and Solar Pro4 share?
17 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Solar Pro4 has 18.