# Gemini 1.5 Pro (May 2024) vs Gemini 3 Pro

> Gemini 3 Pro is the stronger model overall, scoring 54.8 to 32.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-1-5-pro-vs-gemini-3-pro
- Last updated: 2026-10-10
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and Gemini 3 Pro in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Pro leads 52.5 to 12.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 91.4% for Gemini 3 Pro.

## Snapshot

| | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 32.1 | 54.8 |
| Rank | 261 | 28 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 1.5 Pro (May 2024): 34.2 (#241)
- Gemini 3 Pro: 51.6 (#39)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| WeirdML | 22.2% | 69.9% |
| LMArena Coding | 1294 | 1481 |
| SWE-bench Verified | — | 72.9% |
| SWE-bench Verified (bash only) | — | 74.2% |
| LMArena WebDev | — | 1440 |
| SWE-bench Multilingual | — | 68.7% |
| GSO | — | 18.6% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 1,177 |
| AlgoTune | — | 1.83 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |

## Agentic & Tool Use

- Gemini 1.5 Pro (May 2024): 17.9 (#145)
- Gemini 3 Pro: 40.6 (#23)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| BALROG | 21% | 58.1% |
| Terminal-Bench | — | 69.4% |
| Berkeley Function Calling Leaderboard | — | 72.5% |
| GDPval | — | 40.3% |
| Remote Labor Index | — | 1.3% |
| TheAgentCompany | 3.4% | — |
| τ²-bench Airline | — | 80.5% |
| τ²-bench Banking | — | 18% |
| τ²-bench Retail | — | 75.9% |
| τ²-bench Telecom | — | 91% |
| Cybench | 7.5% | — |
| DeepResearch Bench | — | 46.3% |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 71% |
| Vending-Bench 2 | — | 5,478 |

## Reasoning

- Gemini 1.5 Pro (May 2024): 12.3 (#338)
- Gemini 3 Pro: 52.5 (#31)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| ARC-AGI-2 | 0.8% | 31.1% |
| SimpleBench | 27.1% | 76.4% |
| LMArena Hard Prompts | 1296 | 1480 |
| Epoch Capabilities Index | 131.73 | 152.92 |
| ForecastBench | 58.4 | 61.2 |
| Kagi LLM Benchmark | — | 80.1% |
| NYT Connections (extended) | — | 94.4% |
| ARC-AGI-1 | — | 75% |
| CritPt | — | 6.9% |
| Chess Puzzles | — | 31% |
| EnigmaEval | — | 18.2% |
| DTBench | 59% | — |
| BIG-Bench Hard | 89.2% | — |

## Math

- Gemini 1.5 Pro (May 2024): 25.8 (#266)
- Gemini 3 Pro: 49.9 (#59)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 91.4% |
| Omni-MATH | 36.4% | 55.5% |
| LMArena Math | 1315 | 1476 |
| MathArena Final-Answer Competitions | — | 67% |
| ProofBench | — | 20% |
| MATH Level 5 | 70.4% | — |
| FrontierMath (Feb 2025 set) | — | 37.6% |
| FrontierMath Tier 4 (v1) | — | 18.8% |

## Knowledge

- Gemini 1.5 Pro (May 2024): 29.4 (#239)
- Gemini 3 Pro: 64.4 (#16)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| GPQA Diamond | 57.2% | 92.6% |
| Humanity's Last Exam | 4.6% | 37.5% |
| MMLU-Pro | 73.7% | 90.3% |
| GPQA (HELM) | 53.4% | 80.3% |
| LMArena Expert | 1279 | 1475 |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 13.6% |
| MMLU | 86.9% | — |

## Multimodal

- Gemini 1.5 Pro (May 2024): 36.8 (#77)
- Gemini 3 Pro: 57.6 (#2)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| LMArena Vision | 1161 | 1305 |
| Video-MME | 75% | — |
| GeoBench | — | 84% |
| VPCT | — | 91% |
| LMArena Document | — | 1434 |

## Multilingual

- Gemini 1.5 Pro (May 2024): 45.3 (#174)
- Gemini 3 Pro: 56.9 (#16)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| LMArena Non-English | 1312 | 1474 |
| LMArena Chinese | 1331 | 1523 |
| LMArena French | 1302 | 1492 |
| LMArena German | 1286 | 1515 |
| LMArena Japanese | 1292 | 1510 |
| LMArena Korean | 1298 | 1448 |
| LMArena Russian | 1320 | 1493 |
| LMArena Spanish | 1311 | 1470 |

## Instruction Following

- Gemini 1.5 Pro (May 2024): 68.6 (#185)
- Gemini 3 Pro: 76.3 (#45)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| IFEval | 83.7% | 87.7% |
| LMArena Instruction Following | 1297 | 1458 |

## Long Context

- Gemini 1.5 Pro (May 2024): 39.8 (#169)
- Gemini 3 Pro: 44.0 (#79)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| LMArena Longer Query | 1308 | 1471 |
| CL-bench | — | 15.8% |

## Writing & Preference

- Gemini 1.5 Pro (May 2024): 52.4 (#172)
- Gemini 3 Pro: 66.4 (#35)

| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3 Pro |
|---|---|---|
| LMArena Text | 1319 | 1479 |
| LMArena Creative Writing | 1333 | 1482 |
| WildBench | 81.3% | 85.9% |
| LMArena Multi-Turn | 1296 | 1484 |
| EQ-Bench Creative Writing | — | 1525 |

## FAQ

### Is Gemini 1.5 Pro (May 2024) better than Gemini 3 Pro?

Gemini 3 Pro is the stronger model overall, scoring 54.8 to 32.1 on the Noometry Index.

### Is Gemini 1.5 Pro (May 2024) or Gemini 3 Pro better for coding?

Gemini 3 Pro scores higher on coding benchmarks: 51.6 versus 34.2 in the Noometry coding category.

### How many benchmarks do Gemini 1.5 Pro (May 2024) and Gemini 3 Pro share?

32 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Gemini 3 Pro has 67.