Compare · ModelsLive · 2 picked · head to head
gpt-oss-120b vs Claude Opus 4.5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Opus 4.5 wins on 9/11 benchmarks
Claude Opus 4.5 wins 9 of 11 shared benchmarks. Leads in agentic · arena · knowledge.
Category leads
agentic·Claude Opus 4.5arena·Claude Opus 4.5knowledge·Claude Opus 4.5math·gpt-oss-120bsafety·Claude Opus 4.5reasoning·Claude Opus 4.5coding·Claude Opus 4.5
Hype vs Reality
Attention vs performance
gpt-oss-120b
#106 by perf·no signal
Claude Opus 4.5
#111 by perf·no signal
Best value
gpt-oss-120b
135.3x better value than Claude Opus 4.5
gpt-oss-120b
409.6 pts/$
$0.11/M
Claude Opus 4.5
3.0 pts/$
$15.00/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Anthropic
$380.0B·Tier 1
Head to head
11 benchmarks · 2 models
gpt-oss-120bClaude Opus 4.5
APEX-Agents
Claude Opus 4.5 leads by +13.7
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
gpt-oss-120b
4.7
Claude Opus 4.5
18.4
Chatbot Arena Elo · Overall
Claude Opus 4.5 leads by +113.9
gpt-oss-120b
1353.8
Claude Opus 4.5
1467.7
Chess Puzzles
gpt-oss-120b leads by +8.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
gpt-oss-120b
20.0
Claude Opus 4.5
12.0
GPQA diamond
Claude Opus 4.5 leads by +13.7
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
Claude Opus 4.5
81.4
OTIS Mock AIME 2024-2025
gpt-oss-120b leads by +2.8
OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
gpt-oss-120b
88.9
Claude Opus 4.5
86.1
Fortress
Claude Opus 4.5 leads by +5.3
gpt-oss-120b
8.2
Claude Opus 4.5
13.6
SimpleBench
Claude Opus 4.5 leads by +47.9
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
gpt-oss-120b
6.5
Claude Opus 4.5
54.4
SimpleQA Verified
Claude Opus 4.5 leads by +27.9
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
gpt-oss-120b
13.9
Claude Opus 4.5
41.8
SWE-Bench Verified (Bash Only)
Claude Opus 4.5 leads by +48.4
SWE-Bench Verified (Bash Only) · a curated subset of SWE-bench where models fix real Python repository bugs using only bash commands, no agent frameworks.
gpt-oss-120b
26.0
Claude Opus 4.5
74.4
Terminal Bench
Claude Opus 4.5 leads by +44.4
Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency.
gpt-oss-120b
18.7
Claude Opus 4.5
63.1
WeirdML
Claude Opus 4.5 leads by +15.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
gpt-oss-120b
48.2
Claude Opus 4.5
63.7
Full benchmark table
| Benchmark | gpt-oss-120b | Claude Opus 4.5 |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 4.7 | 18.4 |
Chatbot Arena Elo · Overall | 1353.8 | 1467.7 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 20.0 | 12.0 |
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 | 81.4 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 88.9 | 86.1 |
Fortress | 8.2 | 13.6 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 6.5 | 54.4 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 13.9 | 41.8 |
SWE-Bench Verified (Bash Only) SWE-Bench Verified (Bash Only) · a curated subset of SWE-bench where models fix real Python repository bugs using only bash commands, no agent frameworks. | 26.0 | 74.4 |
Terminal Bench Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency. | 18.7 | 63.1 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 48.2 | 63.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| gpt-oss-120b | $0.04 | $0.19 | 131K tokens (~66 books) | $0.77 |
| Claude Opus 4.5 | $5.00 | $25.00 | 200K tokens (~100 books) | $100.00 |
People also compared