Model comparison
GPT-5.4 Pro vs Phi 3 Medium 4k Instruct
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 32.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in reasoning, where GPT-5.4 Pro leads 71.0 to 20.8.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 58.8 | 32.4 |
| Released | 2026-03-05 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $180 | — |
| Results tracked | 16 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
GPT-5.4 Pro: 42.6 (#89), Phi 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | GPT-5.4 Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1130 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 71.0 (#10), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | GPT-5.4 Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 58.6% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1127 |
| Epoch Capabilities Index | 159.12 | — |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.0 (#17), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | GPT-5.4 Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| LMArena Math | — | 1173 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#6), Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | GPT-5.4 Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| GPQA Diamond | 94.6% | — |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1108 |
Multilingual Not comparable
GPT-5.4 Pro: —, Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | GPT-5.4 Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | — | 1094 |
| LMArena Chinese | — | 1108 |
| LMArena French | — | 1109 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Russian | — | 1145 |
| LMArena Spanish | — | 1095 |
Instruction Following Not comparable
GPT-5.4 Pro: —, Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | GPT-5.4 Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1114 |
Long Context Not comparable
GPT-5.4 Pro: —, Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | GPT-5.4 Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1120 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | GPT-5.4 Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | — | 1138 |
| LMArena Creative Writing | — | 1106 |
| LMArena Multi-Turn | — | 1088 |
Frequently asked questions
Is GPT-5.4 Pro better than Phi 3 Medium 4k Instruct?
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 32.4 on the Noometry Index.
Is GPT-5.4 Pro or Phi 3 Medium 4k Instruct better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 42.6 versus 32.3 in the Noometry coding category.
How many benchmarks do GPT-5.4 Pro and Phi 3 Medium 4k Instruct share?
0 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.