Model comparison
DeepSeek-V2.5 (Sep 2024) vs Yi-34B
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 27.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Yi-34B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V2.5 (Sep 2024) leads 34.8 to 7.5.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Yi-34B | |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 37.6 | 27.8 |
| Released | 2024-09-06 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Yi-34B: 32.3 (#274)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Yi-34B |
|---|---|---|
| LMArena Coding | 1309 | 1112 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Yi-34B: 21.2 (#226)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Yi-34B: 21.6 (#282)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Yi-34B |
|---|---|---|
| LMArena Math | 1288 | 1114 |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Yi-34B: 7.5 (#309)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Yi-34B |
|---|---|---|
| LMArena Expert | 1266 | 1061 |
| GPQA Diamond | — | 14.7% |
| MMLU | — | 76.3% |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Yi-34B: 29.7 (#264)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Yi-34B |
|---|---|---|
| LMArena Non-English | 1273 | 1079 |
| LMArena Chinese | 1318 | 1176 |
| LMArena French | 1289 | 1081 |
| LMArena German | 1258 | 1042 |
| LMArena Japanese | 1228 | 993 |
| LMArena Korean | 1209 | 959 |
| LMArena Russian | 1289 | 1050 |
| LMArena Spanish | 1248 | 1070 |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Yi-34B: 56.2 (#274)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1280 | 1091 |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Yi-34B: 33.2 (#264)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1301 | 1094 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Yi-34B: 34.1 (#273)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Yi-34B |
|---|---|---|
| LMArena Text | 1294 | 1129 |
| LMArena Creative Writing | 1285 | 1108 |
| LMArena Multi-Turn | 1297 | 1113 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Yi-34B?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 27.8 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Yi-34B better for coding?
They score almost the same on coding (31.7 vs 32.3); test both on your own repository before choosing.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Yi-34B share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Yi-34B has 23.