Model comparison
DeepSeek-V2.5 (Sep 2024) vs Phi 3 Medium 4k Instruct
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 32.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Phi 3 Medium 4k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 50.0 to 34.3.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 37.0 | 32.4 |
| Released | 2024-09-06 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Medium 4k Instruct leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), Phi 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1310 | 1130 |
| 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): 24.5 (#145), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1127 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1289 | 1173 |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1266 | 1108 |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1273 | 1094 |
| LMArena Chinese | 1317 | 1108 |
| LMArena French | 1288 | 1109 |
| LMArena German | 1258 | 1101 |
| LMArena Japanese | 1228 | 1042 |
| LMArena Korean | 1209 | 954 |
| LMArena Russian | 1289 | 1145 |
| LMArena Spanish | 1248 | 1095 |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1280 | 1114 |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1301 | 1120 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1294 | 1138 |
| LMArena Creative Writing | 1285 | 1106 |
| LMArena Multi-Turn | 1297 | 1088 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Phi 3 Medium 4k Instruct?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 32.4 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Phi 3 Medium 4k Instruct better for coding?
Phi 3 Medium 4k Instruct scores higher on coding benchmarks: 32.3 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.