Model comparison
Codellama 70b Instruct vs DeepSeek-V3.2-Exp
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
DeepSeekSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and DeepSeek-V3.2-Exp in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.2-Exp leads 62.4 to 33.4.
Side by side
| Codellama 70b Instruct | DeepSeek-V3.2-Exp | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 33.7 | 44.3 |
| Released | — | 2025-09-29 |
| Weights | Open | Open |
| Context window | — | 164K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.26 |
| Output $ / M tokens | — | $0.38 |
| Results tracked | 7 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
Codellama 70b Instruct: 37.6 (#193), DeepSeek-V3.2-Exp: 46.5 (#65)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.2-Exp |
|---|---|---|
| SWE-bench Verified (bash only) | — | 70% |
| Aider Polyglot | — | 74.2% |
| LMArena WebDev | — | 1362 |
| SWE-bench Multilingual | — | 59% |
| SciCode | — | 38.9% |
| WeirdML | — | 39.5% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1454 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, DeepSeek-V3.2-Exp: 32.7 (#59)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.2-Exp |
|---|---|---|
| Terminal-Bench | — | 39.6% |
| APEX-Agents | — | 21.3% |
| Berkeley Function Calling Leaderboard | — | 56.7% |
| TheAgentCompany | — | 42.9% |
| Vending-Bench 2 | — | 1,034 |
Reasoning DeepSeek-V3.2-Exp leads
Codellama 70b Instruct: 20.1 (#242), DeepSeek-V3.2-Exp: 22.1 (#208)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1434 |
| ARC-AGI-2 | — | 4% |
| Kagi LLM Benchmark | — | 52.2% |
| NYT Connections (extended) | — | 36.7% |
| ARC-AGI-1 | — | 57% |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 14% |
| Thematic Generalization | — | 65% |
| DTBench | — | 87.7% |
| LMCA | — | 29.1% |
| Epoch Capabilities Index | — | 146.27 |
Math Not comparable
Codellama 70b Instruct: —, DeepSeek-V3.2-Exp: 41.7 (#87)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.2-Exp |
|---|---|---|
| MathArena Final-Answer Competitions | — | 57.7% |
| OTIS Mock AIME 2024-2025 | — | 87.8% |
| ProofBench | — | 8% |
| LMArena Math | — | 1435 |
| FrontierMath (Feb 2025 set) | — | 22.1% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Not comparable
Codellama 70b Instruct: —, DeepSeek-V3.2-Exp: 51.7 (#66)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.2-Exp |
|---|---|---|
| GPQA Diamond | — | 83.4% |
| Vectara Hallucination Rate | — | 5.3% |
| LMArena Expert | — | 1436 |
Multilingual DeepSeek-V3.2-Exp leads
Codellama 70b Instruct: 24.8 (#288), DeepSeek-V3.2-Exp: 52.2 (#90)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Non-English | 992 | 1409 |
| LMArena Chinese | — | 1461 |
| LMArena French | — | 1433 |
| LMArena German | — | 1440 |
| LMArena Japanese | — | 1374 |
| LMArena Korean | — | 1371 |
| LMArena Russian | — | 1424 |
| LMArena Spanish | — | 1440 |
Instruction Following DeepSeek-V3.2-Exp leads
Codellama 70b Instruct: 51.9 (#293), DeepSeek-V3.2-Exp: 74.5 (#93)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Instruction Following | 1024 | 1413 |
Long Context Not comparable
Codellama 70b Instruct: —, DeepSeek-V3.2-Exp: 47.6 (#16)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.2-Exp |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| CL-bench | — | 13.2% |
| CL-bench Life | — | 9.5% |
| LMArena Longer Query | — | 1428 |
Writing & Preference DeepSeek-V3.2-Exp leads
Codellama 70b Instruct: 33.4 (#277), DeepSeek-V3.2-Exp: 62.4 (#77)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Text | 1057 | 1425 |
| LMArena Creative Writing | — | 1403 |
| EQ-Bench Creative Writing | — | 1515 |
| LMArena Multi-Turn | — | 1427 |
Frequently asked questions
Is Codellama 70b Instruct better than DeepSeek-V3.2-Exp?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or DeepSeek-V3.2-Exp better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and DeepSeek-V3.2-Exp share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and DeepSeek-V3.2-Exp has 49.