# Codellama 70b Instruct vs GPT-6 Sol

> GPT-6 Sol is the stronger model overall, scoring 61.8 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-gpt-6-sol
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and GPT-6 Sol in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 20.1.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 33.7 | 61.8 |
| Rank | 237 | 12 |
| Context | — | 1.05M |
| Input $/M | — | $2 |
| Output $/M | — | $10 |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- GPT-6 Sol: 60.1 (#11)

| Benchmark | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1447 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 2,462 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- GPT-6 Sol: 37.2 (#36)

| Benchmark | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| GDP.pdf | — | 26.4% |
| Vending-Bench 2 | — | 14,428 |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- GPT-6 Sol: 74.0 (#9)

| Benchmark | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1418 |
| ARC-AGI-2 | — | 89.6% |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| EBR-Bench | — | 53.3% |
| Mystery Game Puzzles | — | 56% |
| DTBench | — | 97.3% |
| LMCA | — | 59.1% |
| Epoch Capabilities Index | — | 162.72 |

## Math

- Codellama 70b Instruct: —
- GPT-6 Sol: 87.2 (#7)

| Benchmark | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 83% |
| LMArena Math | — | 1402 |

## Knowledge

- Codellama 70b Instruct: —
- GPT-6 Sol: 64.8 (#15)

| Benchmark | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | — | 94.3% |
| SimpleQA Verified | — | 60.7% |
| Vectara Hallucination Rate | — | 6.5% |
| LMArena Expert | — | 1439 |

## Multimodal

- Codellama 70b Instruct: —
- GPT-6 Sol: 47.6 (#10)

| Benchmark | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| LMArena Vision | — | 1245 |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- GPT-6 Sol: 50.5 (#118)

| Benchmark | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 992 | 1385 |
| LMArena Chinese | — | 1405 |
| LMArena French | — | 1410 |
| LMArena German | — | 1390 |
| LMArena Japanese | — | 1385 |
| LMArena Korean | — | 1341 |
| LMArena Russian | — | 1401 |
| LMArena Spanish | — | 1384 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- GPT-6 Sol: 74.5 (#94)

| Benchmark | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1024 | 1412 |

## Long Context

- Codellama 70b Instruct: —
- GPT-6 Sol: 43.1 (#108)

| Benchmark | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | — | 1411 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- GPT-6 Sol: 71.9 (#18)

| Benchmark | Codellama 70b Instruct | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1057 | 1395 |
| LMArena Creative Writing | — | 1378 |
| EQ-Bench Creative Writing | — | 2125 |
| LMArena Multi-Turn | — | 1412 |

## FAQ

### Is Codellama 70b Instruct better than GPT-6 Sol?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and GPT-6 Sol share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GPT-6 Sol has 45.