# Gemini 3.1 Pro Preview vs Solar Pro4

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 41.5 on the Noometry Index. Solar Pro4 costs 8.6× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-1-pro-preview-vs-solar-pro4
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Solar Pro4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 27.3.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 524K.

## Snapshot

| | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| Provider | Google | Upstage |
| Noometry Index | 56.7 | 41.5 |
| Rank | 20 | 123 |
| Context | 1.05M | 524K |
| Input $/M | $2 | $0.30 |
| Output $/M | $12 | $1.20 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.1 Pro Preview: 42.7 (#88)
- Solar Pro4: 39.9 (#135)

| Benchmark | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| LMArena WebDev | 1446 | 1371 |
| LMArena Coding | 1483 | 1439 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| MirrorCode | 8.9% | — |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#33)
- Solar Pro4: —

| Benchmark | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |

## Reasoning

- Gemini 3.1 Pro Preview: 71.7 (#9)
- Solar Pro4: 27.3 (#107)

| Benchmark | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1484 | 1398 |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| CritPt | 17.7% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| Epoch Capabilities Index | 154.92 | — |
| ForecastBench | 59 | — |

## Math

- Gemini 3.1 Pro Preview: 61.8 (#28)
- Solar Pro4: 36.1 (#129)

| Benchmark | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| LMArena Math | 1485 | 1418 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- Solar Pro4: 39.0 (#128)

| Benchmark | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1484 | 1421 |
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |

## Multimodal

- Gemini 3.1 Pro Preview: 38.1 (#60)
- Solar Pro4: —

| Benchmark | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |

## Multilingual

- Gemini 3.1 Pro Preview: 57.1 (#11)
- Solar Pro4: 49.0 (#134)

| Benchmark | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1475 | 1362 |
| LMArena Chinese | 1528 | 1417 |
| LMArena French | 1488 | 1403 |
| LMArena German | 1491 | 1351 |
| LMArena Japanese | 1494 | 1300 |
| LMArena Korean | 1458 | 1383 |
| LMArena Russian | 1496 | 1360 |
| LMArena Spanish | 1480 | 1408 |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.1 (#31)
- Solar Pro4: 72.8 (#128)

| Benchmark | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1465 | 1376 |

## Long Context

- Gemini 3.1 Pro Preview: 47.3 (#17)
- Solar Pro4: 42.0 (#125)

| Benchmark | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1482 | 1379 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.3 (#36)
- Solar Pro4: 56.7 (#133)

| Benchmark | Gemini 3.1 Pro Preview | Solar Pro4 |
|---|---|---|
| LMArena Text | 1480 | 1386 |
| LMArena Creative Writing | 1482 | 1313 |
| LMArena Multi-Turn | 1486 | 1391 |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |

## FAQ

### Is Gemini 3.1 Pro Preview better than Solar Pro4?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 41.5 on the Noometry Index. Solar Pro4 costs 8.6× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.1 Pro Preview or Solar Pro4?

Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

### Is Gemini 3.1 Pro Preview or Solar Pro4 better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.7 versus 39.9 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 524K.

### How many benchmarks do Gemini 3.1 Pro Preview and Solar Pro4 share?

18 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Solar Pro4 has 18.