Model comparison
Codellama 34b Instruct vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 30.2 on the Noometry Index.
Last verified . 10 shared benchmarks.
MetaSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and MiMo-V2.5 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.8 to 28.4.
Side by side
| Codellama 34b Instruct | MiMo-V2.5 | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 30.2 | 43.0 |
| Released | — | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 14 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
Codellama 34b Instruct: 28.0 (#310), MiMo-V2.5: 43.6 (#75)
| Benchmark | Codellama 34b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1046 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 513.95 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning MiMo-V2.5 leads
Codellama 34b Instruct: 18.8 (#250), MiMo-V2.5: 27.8 (#98)
| Benchmark | Codellama 34b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1450 |
| CritPt | — | 3.7% |
Math MiMo-V2.5 leads
Codellama 34b Instruct: 28.5 (#227), MiMo-V2.5: 35.4 (#145)
| Benchmark | Codellama 34b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1056 | 1436 |
| ProofBench | — | 16% |
Knowledge Not comparable
Codellama 34b Instruct: —, MiMo-V2.5: 40.2 (#109)
| Benchmark | Codellama 34b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | — | 1459 |
Multimodal Not comparable
Codellama 34b Instruct: —, MiMo-V2.5: 39.0 (#53)
| Benchmark | Codellama 34b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual MiMo-V2.5 leads
Codellama 34b Instruct: 25.9 (#279), MiMo-V2.5: 52.0 (#96)
| Benchmark | Codellama 34b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1011 | 1404 |
| LMArena Chinese | 976 | 1467 |
| LMArena French | — | 1447 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1304 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1395 |
| LMArena Spanish | — | 1412 |
Instruction Following MiMo-V2.5 leads
Codellama 34b Instruct: 52.4 (#286), MiMo-V2.5: 75.7 (#55)
| Benchmark | Codellama 34b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1433 |
Long Context MiMo-V2.5 leads
Codellama 34b Instruct: 30.8 (#279), MiMo-V2.5: 44.1 (#69)
| Benchmark | Codellama 34b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1014 | 1444 |
Writing & Preference MiMo-V2.5 leads
Codellama 34b Instruct: 28.4 (#292), MiMo-V2.5: 61.8 (#82)
| Benchmark | Codellama 34b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1066 | 1427 |
| LMArena Creative Writing | 1032 | 1392 |
| LMArena Multi-Turn | 1015 | 1445 |
Frequently asked questions
Is Codellama 34b Instruct better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 30.2 on the Noometry Index.
Is Codellama 34b Instruct or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and MiMo-V2.5 share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and MiMo-V2.5 has 23.