Model comparison
DeepSeek-V3.1 vs Yi-34B
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 27.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
DeepSeekSummary
- They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.0 to 7.5.
Side by side
| DeepSeek-V3.1 | Yi-34B | |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 42.2 | 27.4 |
| Released | 2025-08-21 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 39.8 (#140), Yi-34B: 31.8 (#269)
| Benchmark | DeepSeek-V3.1 | Yi-34B |
|---|---|---|
| LMArena Coding | 1417 | 1112 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.3 (#109), Yi-34B: 20.3 (#222)
| Benchmark | DeepSeek-V3.1 | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1104 |
| Epoch Capabilities Index | 139.92 | 117.28 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| BIG-Bench Hard | — | 71.7% |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.1 (#125), Yi-34B: 19.8 (#277)
| Benchmark | DeepSeek-V3.1 | Yi-34B |
|---|---|---|
| LMArena Math | 1420 | 1114 |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.0 (#86), Yi-34B: 7.5 (#304)
| Benchmark | DeepSeek-V3.1 | Yi-34B |
|---|---|---|
| LMArena Expert | 1403 | 1061 |
| GPQA Diamond | — | 14.7% |
| Vectara Hallucination Rate | 5.5% | — |
| MMLU | — | 76.3% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.8 (#100), Yi-34B: 29.9 (#259)
| Benchmark | DeepSeek-V3.1 | Yi-34B |
|---|---|---|
| LMArena Non-English | 1400 | 1079 |
| LMArena Chinese | 1470 | 1175 |
| LMArena French | 1447 | 1080 |
| LMArena German | 1412 | 1042 |
| LMArena Japanese | 1374 | 993 |
| LMArena Korean | 1337 | 959 |
| LMArena Russian | 1405 | 1050 |
| LMArena Spanish | 1429 | 1070 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 74.1 (#105), Yi-34B: 56.4 (#269)
| Benchmark | DeepSeek-V3.1 | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1091 |
Long Context DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.3 (#227), Yi-34B: 33.2 (#259)
| Benchmark | DeepSeek-V3.1 | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1422 | 1094 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.5 (#93), Yi-34B: 34.3 (#268)
| Benchmark | DeepSeek-V3.1 | Yi-34B |
|---|---|---|
| LMArena Text | 1420 | 1129 |
| LMArena Creative Writing | 1401 | 1108 |
| LMArena Multi-Turn | 1408 | 1113 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Yi-34B?
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 27.4 on the Noometry Index.
Is DeepSeek-V3.1 or Yi-34B better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 31.8 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Yi-34B share?
18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Yi-34B has 23.