# Codellama 70b Instruct vs Gemini 3.8 Flash

> Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 33.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-gemini-3-8-flash
- 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 Gemini 3.8 Flash in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 64.7 to 19.2.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| Provider | Meta | Google |
| Noometry Index | 33.3 | 59.5 |
| Rank | 236 | 13 |
| Context | — | 1.05M |
| Input $/M | — | $0.75 |
| Output $/M | — | $3.75 |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- Gemini 3.8 Flash: 56.4 (#17)

| Benchmark | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| CursorBench | — | 39.6% |
| LMArena WebDev | — | 1581 |
| FrontierSWE | — | 19.6% |
| SciCode | — | 56.6% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1512 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 1,270 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Gemini 3.8 Flash: 40.3 (#22)

| Benchmark | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- Gemini 3.8 Flash: 64.7 (#13)

| Benchmark | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1506 |
| NYT Connections (extended) | — | 97.4% |
| CritPt | — | 18.3% |
| Chess Puzzles | — | 61% |
| Mystery Game Puzzles | — | 47% |
| DTBench | — | 95.7% |
| LMCA | — | 52.9% |
| Surface Evolver Bench | — | 76.9% |
| Epoch Capabilities Index | — | 157.13 |

## Math

- Codellama 70b Instruct: —
- Gemini 3.8 Flash: 65.2 (#22)

| Benchmark | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 68.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 48% |
| LMArena Math | — | 1528 |

## Knowledge

- Codellama 70b Instruct: —
- Gemini 3.8 Flash: 74.9 (#2)

| Benchmark | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | — | 95.4% |
| Humanity's Last Exam | — | 44.5% |
| SimpleQA Verified | — | 69.7% |
| LMArena Expert | — | 1529 |

## Multimodal

- Codellama 70b Instruct: —
- Gemini 3.8 Flash: 40.9 (#33)

| Benchmark | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | — | 1312 |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- Gemini 3.8 Flash: 57.9 (#5)

| Benchmark | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 992 | 1486 |
| LMArena Chinese | — | 1547 |
| LMArena French | — | 1502 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1505 |
| LMArena Korean | — | 1479 |
| LMArena Russian | — | 1507 |
| LMArena Spanish | — | 1492 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- Gemini 3.8 Flash: 78.2 (#11)

| Benchmark | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1024 | 1489 |

## Long Context

- Codellama 70b Instruct: —
- Gemini 3.8 Flash: 46.2 (#23)

| Benchmark | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | — | 1506 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- Gemini 3.8 Flash: 72.1 (#16)

| Benchmark | Codellama 70b Instruct | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1057 | 1494 |
| LMArena Creative Writing | — | 1485 |
| EQ-Bench Creative Writing | — | 1748 |
| LMArena Multi-Turn | — | 1503 |

## FAQ

### Is Codellama 70b Instruct better than Gemini 3.8 Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 33.3 on the Noometry Index.

### Is Codellama 70b Instruct or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 56.4 versus 37.0 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Gemini 3.8 Flash share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Gemini 3.8 Flash has 46.