Compare · ModelsLive · 2 picked · head to head
gpt-oss-120b vs Phi 4
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
gpt-oss-120b wins on 4/4 benchmarks
gpt-oss-120b wins 4 of 4 shared benchmarks. Leads in arena · knowledge · math.
Category leads
arena·gpt-oss-120bknowledge·gpt-oss-120bmath·gpt-oss-120b
Hype vs Reality
Attention vs performance
gpt-oss-120b
#137 by perf·no signal
Phi 4
#155 by perf·no signal
Best value
gpt-oss-120b
1.1x better value than Phi 4
gpt-oss-120b
434.3 pts/$
$0.11/M
Phi 4
411.4 pts/$
$0.11/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Microsoft
$3.00T·Big Tech
Head to head
4 benchmarks · 2 models
gpt-oss-120bPhi 4
Chatbot Arena Elo · Overall
gpt-oss-120b leads by +96.7
gpt-oss-120b
1352.7
Phi 4
1256.0
GPQA diamond
gpt-oss-120b leads by +26.3
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
gpt-oss-120b
67.7
Phi 4
41.4
Lech Mazur Writing
gpt-oss-120b leads by +14.7
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
gpt-oss-120b
77.3
Phi 4
62.6
OTIS Mock AIME 2024-2025
gpt-oss-120b leads by +75.2
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
gpt-oss-120b
88.9
Phi 4
13.7
Full benchmark table
| Benchmark | gpt-oss-120b | Phi 4 |
|---|---|---|
Chatbot Arena Elo · Overall | 1352.7 | 1256.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 67.7 | 41.4 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 77.3 | 62.6 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 88.9 | 13.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.04 | $0.18 | 131K tokens (~66 books) | $0.72 | |
| $0.07 | $0.14 | 16K tokens (~8 books) | $0.88 |