Model comparison
DeepSeek-V3.1 vs Phi 3 Mini 4k Instruct
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 17 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 27.6.
Side by side
| DeepSeek-V3.1 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 42.8 | 27.9 |
| Released | 2025-08-21 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | DeepSeek-V3.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1417 | 1093 |
| WeirdML | 38.4% | — |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | DeepSeek-V3.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1072 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 82.7% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 24.3% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | DeepSeek-V3.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1420 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | DeepSeek-V3.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1405 | 1045 |
| Vectara Hallucination Rate | 5.5% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | DeepSeek-V3.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1400 | 1021 |
| LMArena Chinese | 1469 | 1021 |
| LMArena French | 1447 | 1076 |
| LMArena German | 1411 | 1044 |
| LMArena Japanese | 1378 | 935 |
| LMArena Korean | 1337 | 905 |
| LMArena Russian | 1405 | 1022 |
| LMArena Spanish | 1431 | 1085 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | DeepSeek-V3.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1400 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.3 (#232), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | DeepSeek-V3.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1422 | 1044 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | DeepSeek-V3.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1420 | 1073 |
| LMArena Creative Writing | 1401 | 1037 |
| LMArena Multi-Turn | 1408 | 1018 |
| EQ-Bench Creative Writing | 1436 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is DeepSeek-V3.1 better than Phi 3 Mini 4k Instruct?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 27.9 on the Noometry Index.
Is DeepSeek-V3.1 or Phi 3 Mini 4k Instruct better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 26.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Phi 3 Mini 4k Instruct share?
17 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.