# Gemini 1.5 Pro (May 2024) vs Gemini 3.1 Pro Preview

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-1-5-pro-vs-gemini-3-1-pro-preview
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and Gemini 3.1 Pro Preview in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 12.3.
- The biggest single-benchmark swing is ARC-AGI-2: 0.8% for Gemini 1.5 Pro (May 2024) and 77.1% for Gemini 3.1 Pro Preview.

## Snapshot

| | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 31.9 | 56.7 |
| Rank | 253 | 20 |
| Context | — | 1.05M |
| Input $/M | — | $2 |
| Output $/M | — | $12 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 1.5 Pro (May 2024): 33.8 (#239)
- Gemini 3.1 Pro Preview: 42.7 (#88)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| WeirdML | 22.2% | 72.1% |
| LMArena Coding | 1294 | 1483 |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| LMArena WebDev | — | 1446 |
| SciCode | — | 58.9% |
| GSO | — | 22.6% |
| BigCodeBench Instruct | 43.8% | — |
| MirrorCode | — | 8.9% |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 1,161 |
| AlgoTune | — | 2.02 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |

## Agentic & Tool Use

- Gemini 1.5 Pro (May 2024): 17.8 (#137)
- Gemini 3.1 Pro Preview: 37.7 (#33)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| BALROG | 21% | 57% |
| Terminal-Bench | — | 80.2% |
| APEX-Agents | — | 35.3% |
| TheAgentCompany | 3.4% | — |
| τ²-bench Banking | — | 26% |
| Cybench | 7.5% | — |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| LMArena Search | — | 1211 |
| METR Time Horizons | — | 77% |
| Vending-Bench 2 | — | 3,774 |

## Reasoning

- Gemini 1.5 Pro (May 2024): 12.3 (#332)
- Gemini 3.1 Pro Preview: 71.7 (#9)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| ARC-AGI-2 | 0.8% | 77.1% |
| SimpleBench | 27.1% | 79.6% |
| LMArena Hard Prompts | 1296 | 1484 |
| DTBench | 59% | 97.1% |
| Epoch Capabilities Index | 131.73 | 154.92 |
| ForecastBench | 58.4 | 59 |
| 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% |
| LMCA | — | 53.8% |
| BIG-Bench Hard | 89.2% | — |

## Math

- Gemini 1.5 Pro (May 2024): 24.4 (#260)
- Gemini 3.1 Pro Preview: 61.8 (#28)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 95.6% |
| LMArena Math | 1315 | 1485 |
| FrontierMath (Tiers 1-3) | — | 59.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 86.5% |
| ProofBench | — | 26% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |

## Knowledge

- Gemini 1.5 Pro (May 2024): 29.3 (#228)
- Gemini 3.1 Pro Preview: 71.8 (#3)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | 57.2% | 94.4% |
| Humanity's Last Exam | 4.6% | 46.4% |
| LMArena Expert | 1279 | 1484 |
| SimpleQA Verified | — | 73.5% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 10.4% |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |

## Multimodal

- Gemini 1.5 Pro (May 2024): 36.2 (#72)
- Gemini 3.1 Pro Preview: 38.1 (#60)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | 1161 | 1296 |
| Video-MME | 75% | — |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |

## Multilingual

- Gemini 1.5 Pro (May 2024): 45.5 (#169)
- Gemini 3.1 Pro Preview: 57.1 (#11)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1312 | 1475 |
| LMArena Chinese | 1331 | 1528 |
| LMArena French | 1301 | 1488 |
| LMArena German | 1286 | 1491 |
| LMArena Japanese | 1292 | 1494 |
| LMArena Korean | 1298 | 1458 |
| LMArena Russian | 1320 | 1496 |
| LMArena Spanish | 1310 | 1480 |

## Instruction Following

- Gemini 1.5 Pro (May 2024): 68.8 (#180)
- Gemini 3.1 Pro Preview: 77.1 (#31)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1297 | 1465 |
| IFEval | 83.7% | — |

## Long Context

- Gemini 1.5 Pro (May 2024): 39.7 (#164)
- Gemini 3.1 Pro Preview: 47.3 (#17)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1308 | 1482 |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |

## Writing & Preference

- Gemini 1.5 Pro (May 2024): 52.5 (#167)
- Gemini 3.1 Pro Preview: 66.3 (#36)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1319 | 1480 |
| LMArena Creative Writing | 1333 | 1482 |
| LMArena Multi-Turn | 1296 | 1486 |
| EQ-Bench Creative Writing | — | 1491 |
| WildBench | 81.3% | — |
| EQ-Bench 4 | — | 1142 |

## FAQ

### Is Gemini 1.5 Pro (May 2024) better than Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 31.9 on the Noometry Index.

### Is Gemini 1.5 Pro (May 2024) or Gemini 3.1 Pro Preview better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.7 versus 33.8 in the Noometry coding category.

### How many benchmarks do Gemini 1.5 Pro (May 2024) and Gemini 3.1 Pro Preview share?

28 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Gemini 3.1 Pro Preview has 71.