Model comparison
GPT-5.1-Codex vs Phi 3 Mini 4k Instruct
GPT-5.1-Codex is the stronger model overall, scoring 38.6 to 27.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in coding, where GPT-5.1-Codex leads 41.9 to 26.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1-Codex | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 38.6 | 27.9 |
| Released | 2025-11-12 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 6 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1-Codex leads
GPT-5.1-Codex: 41.9 (#116), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | GPT-5.1-Codex | Phi 3 Mini 4k Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 66% | — |
| LMArena WebDev | 1337 | — |
| LiveBench Coding | — | 15.5% |
| LMArena Coding | — | 1093 |
| ALE-Bench | 1,245 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
GPT-5.1-Codex: 38.0 (#33), Phi 3 Mini 4k Instruct: —
| Benchmark | GPT-5.1-Codex | Phi 3 Mini 4k Instruct |
|---|---|---|
| Terminal-Bench | 60.4% | — |
| METR Time Horizons | 70.8% | — |
Reasoning Not comparable
GPT-5.1-Codex: —, Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | GPT-5.1-Codex | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LMArena Hard Prompts | — | 1072 |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math GPT-5.1-Codex leads
GPT-5.1-Codex: 30.3 (#235), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | GPT-5.1-Codex | Phi 3 Mini 4k Instruct |
|---|---|---|
| ProofBench | 9% | — |
| LiveBench Math | — | 15.7% |
| LMArena Math | — | 1111 |
Knowledge Not comparable
GPT-5.1-Codex: —, Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | GPT-5.1-Codex | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | — | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Not comparable
GPT-5.1-Codex: —, Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | GPT-5.1-Codex | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | — | 1021 |
| LMArena Chinese | — | 1021 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Russian | — | 1022 |
| LMArena Spanish | — | 1085 |
Instruction Following Not comparable
GPT-5.1-Codex: —, Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | GPT-5.1-Codex | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | — | 39.1% |
| LMArena Instruction Following | — | 1053 |
Long Context Not comparable
GPT-5.1-Codex: —, Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | GPT-5.1-Codex | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1044 |
Writing & Preference Not comparable
GPT-5.1-Codex: —, Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | GPT-5.1-Codex | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | — | 1073 |
| LMArena Creative Writing | — | 1037 |
| LMArena Multi-Turn | — | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is GPT-5.1-Codex better than Phi 3 Mini 4k Instruct?
GPT-5.1-Codex is the stronger model overall, scoring 38.6 to 27.9 on the Noometry Index.
Is GPT-5.1-Codex or Phi 3 Mini 4k Instruct better for coding?
GPT-5.1-Codex scores higher on coding benchmarks: 41.9 versus 26.6 in the Noometry coding category.
How many benchmarks do GPT-5.1-Codex and Phi 3 Mini 4k Instruct share?
0 benchmarks have published results for both models. GPT-5.1-Codex has 6 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.