Model comparison
Codellama 34b Instruct vs DeepSeek V4 Flash
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
DeepSeekSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and DeepSeek V4 Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek V4 Flash leads 63.8 to 28.2.
Side by side
| Codellama 34b Instruct | DeepSeek V4 Flash | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 30.8 | 53.6 |
| Released | — | 2026-04-24 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 393K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 14 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
Codellama 34b Instruct: 28.5 (#314), DeepSeek V4 Flash: 47.9 (#59)
| Benchmark | Codellama 34b Instruct | DeepSeek V4 Flash |
|---|---|---|
| LMArena Coding | 1046 | 1457 |
| FrontierCode | — | 18.8% |
| LMArena WebDev | — | 1582 |
| SciCode | — | 49.9% |
| WeirdML | — | 63% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 1,306 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning DeepSeek V4 Flash leads
Codellama 34b Instruct: 19.6 (#255), DeepSeek V4 Flash: 53.7 (#30)
| Benchmark | Codellama 34b Instruct | DeepSeek V4 Flash |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1444 |
| ARC-AGI-2 | — | 61.4% |
| SimpleBench | — | 61.1% |
| Kagi LLM Benchmark | — | 52.2% |
| NYT Connections (extended) | — | 89.6% |
| ARC-AGI-1 | — | 89% |
| CritPt | — | 16.6% |
| Chess Puzzles | — | 33% |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 90.9% |
| LMCA | — | 41.7% |
| Epoch Capabilities Index | — | 154.49 |
Math DeepSeek V4 Flash leads
Codellama 34b Instruct: 31.0 (#230), DeepSeek V4 Flash: 60.3 (#37)
| Benchmark | Codellama 34b Instruct | DeepSeek V4 Flash |
|---|---|---|
| LMArena Math | 1056 | 1427 |
| FrontierMath (Tiers 1-3) | — | 57.5% |
| FrontierMath Tier 4 | — | 24.4% |
| MathArena Final-Answer Competitions | — | 76.5% |
| OTIS Mock AIME 2024-2025 | — | 94.4% |
| ProofBench | — | 56% |
Knowledge Not comparable
Codellama 34b Instruct: —, DeepSeek V4 Flash: 55.4 (#48)
| Benchmark | Codellama 34b Instruct | DeepSeek V4 Flash |
|---|---|---|
| GPQA Diamond | — | 91% |
| SimpleQA Verified | — | 33.6% |
| LMArena Expert | — | 1441 |
Multilingual DeepSeek V4 Flash leads
Codellama 34b Instruct: 25.8 (#284), DeepSeek V4 Flash: 53.0 (#72)
| Benchmark | Codellama 34b Instruct | DeepSeek V4 Flash |
|---|---|---|
| LMArena Non-English | 1011 | 1420 |
| LMArena Chinese | 976 | 1468 |
| LMArena French | — | 1439 |
| LMArena German | — | 1418 |
| LMArena Japanese | — | 1406 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1436 |
Instruction Following DeepSeek V4 Flash leads
Codellama 34b Instruct: 52.2 (#291), DeepSeek V4 Flash: 74.9 (#81)
| Benchmark | Codellama 34b Instruct | DeepSeek V4 Flash |
|---|---|---|
| LMArena Instruction Following | 1028 | 1421 |
Long Context DeepSeek V4 Flash leads
Codellama 34b Instruct: 30.9 (#284), DeepSeek V4 Flash: 43.8 (#85)
| Benchmark | Codellama 34b Instruct | DeepSeek V4 Flash |
|---|---|---|
| LMArena Longer Query | 1013 | 1434 |
Writing & Preference DeepSeek V4 Flash leads
Codellama 34b Instruct: 28.2 (#297), DeepSeek V4 Flash: 63.8 (#61)
| Benchmark | Codellama 34b Instruct | DeepSeek V4 Flash |
|---|---|---|
| LMArena Text | 1066 | 1432 |
| LMArena Creative Writing | 1032 | 1403 |
| LMArena Multi-Turn | 1015 | 1449 |
| EQ-Bench Creative Writing | — | 1559 |
Frequently asked questions
Is Codellama 34b Instruct better than DeepSeek V4 Flash?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or DeepSeek V4 Flash better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and DeepSeek V4 Flash share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and DeepSeek V4 Flash has 41.