# Codellama 70b Instruct vs Gemini 3.1 Pro Preview

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-gemini-3-1-pro-preview
- Last updated: 2026-10-12
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Gemini 3.1 Pro Preview in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 20.1.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| Provider | Meta | Google |
| Noometry Index | 33.7 | 56.7 |
| Rank | 237 | 23 |
| Context | — | 1.05M |
| Input $/M | — | $2 |
| Output $/M | — | $12 |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Gemini 3.1 Pro Preview: 42.5 (#99)

| Benchmark | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| LMArena WebDev | — | 1447 |
| SciCode | — | 58.9% |
| GSO | — | 22.6% |
| WeirdML | — | 72.1% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1484 |
| MirrorCode | — | 8.9% |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 1,161 |
| AlgoTune | — | 2.02 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Gemini 3.1 Pro Preview: 37.7 (#34)

| Benchmark | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| 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

- Codellama 70b Instruct: 20.1 (#242)
- Gemini 3.1 Pro Preview: 71.7 (#12)

| Benchmark | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1485 |
| 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 | — | 154.77 |
| ForecastBench | — | 59 |

## Math

- Codellama 70b Instruct: —
- Gemini 3.1 Pro Preview: 62.1 (#34)

| Benchmark | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| 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% |
| LMArena Math | — | 1485 |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |

## Knowledge

- Codellama 70b Instruct: —
- Gemini 3.1 Pro Preview: 71.8 (#3)

| Benchmark | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | — | 94.4% |
| Humanity's Last Exam | — | 46.4% |
| SimpleQA Verified | — | 73.5% |
| Vectara Hallucination Rate | — | 10.4% |
| LMArena Expert | — | 1485 |

## Multimodal

- Codellama 70b Instruct: —
- Gemini 3.1 Pro Preview: 37.9 (#69)

| Benchmark | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | — | 1296 |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Gemini 3.1 Pro Preview: 57.0 (#12)

| Benchmark | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 992 | 1477 |
| LMArena Chinese | — | 1529 |
| LMArena French | — | 1487 |
| LMArena German | — | 1491 |
| LMArena Japanese | — | 1493 |
| LMArena Korean | — | 1455 |
| LMArena Russian | — | 1498 |
| LMArena Spanish | — | 1479 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Gemini 3.1 Pro Preview: 77.0 (#32)

| Benchmark | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1024 | 1466 |

## Long Context

- Codellama 70b Instruct: —
- Gemini 3.1 Pro Preview: 47.4 (#18)

| Benchmark | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
| LMArena Longer Query | — | 1483 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Gemini 3.1 Pro Preview: 66.1 (#37)

| Benchmark | Codellama 70b Instruct | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1057 | 1481 |
| LMArena Creative Writing | — | 1482 |
| EQ-Bench Creative Writing | — | 1491 |
| EQ-Bench 4 | — | 1142 |
| LMArena Multi-Turn | — | 1488 |

## FAQ

### Is Codellama 70b Instruct better than Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Gemini 3.1 Pro Preview better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Gemini 3.1 Pro Preview share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Gemini 3.1 Pro Preview has 71.