BlogLLM Benchmark Scores as Published, Side by Side
Phi-4-reasoning-plus: Benchmark Scores as Published
Every result the catalog holds for Phi-4-reasoning-plus: 4 tests in 1 area, from 2 pages. Each was printed by the company named beside it. Each number is as printed; nothing is ranked or rescored.
Developer MicrosoftReleased 2025-04-30Context window 32KInput TextOutput TextWeights Open (MIT)Data version 2026103001, as of 2026-10-30
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 69.3% | DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15 | - |
| AIME 2025 | 78% | DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15 | - |
| HMMT February 2025 | 53.6% | DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15 | - |
| AIME 2024 | 81.3% | DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15 | - |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Input | $0.125 | Microsoft, Microsoft Foundry Models pricing, Microsoft modelschecked 2026-10-19 | - |
| Output | $0.5 | Microsoft, Microsoft Foundry Models pricing, Microsoft modelschecked 2026-10-19 | - |
More from Microsoft
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.