Compare · ModelsLive · 2 picked · head to head
Claude Haiku 4.5 vs gpt-oss-120b
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
gpt-oss-120b wins on 6/9 benchmarks
gpt-oss-120b wins 6 of 9 shared benchmarks. Leads in knowledge · general · math.
Category leads
agentic·Claude Haiku 4.5knowledge·gpt-oss-120bgeneral·gpt-oss-120bmath·gpt-oss-120bcoding·Claude Haiku 4.5
Hype vs Reality
Attention vs performance
Claude Haiku 4.5
#231 by perf·#13 by attention
gpt-oss-120b
#127 by perf·no signal
Best value
gpt-oss-120b
41.9x better value than Claude Haiku 4.5
Claude Haiku 4.5
11.3 pts/$
$3.00/M
gpt-oss-120b
475.4 pts/$
$0.10/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
9 benchmarks · 2 models
Claude Haiku 4.5gpt-oss-120b
APEX-Agents
Claude Haiku 4.5 leads by +4.5
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Haiku 4.5
8.9
gpt-oss-120b
4.4
Chess Puzzles
gpt-oss-120b leads by +12.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Haiku 4.5
3.2
gpt-oss-120b
15.8
Dtbench
gpt-oss-120b leads by +4.5
Claude Haiku 4.5
56.0
gpt-oss-120b
60.5
GPQA diamond
gpt-oss-120b leads by +6.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Haiku 4.5
61.6
gpt-oss-120b
67.7
Lmca
Claude Haiku 4.5 leads by +10.3
Claude Haiku 4.5
36.4
gpt-oss-120b
26.1
OTIS Mock AIME 2024-2025
gpt-oss-120b leads by +22.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Haiku 4.5
66.6
gpt-oss-120b
88.9
SimpleQA Verified
gpt-oss-120b leads by +0.7
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Haiku 4.5
13.2
gpt-oss-120b
13.9
Terminal Bench
Claude Haiku 4.5 leads by +16.8
Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence.
Claude Haiku 4.5
35.5
gpt-oss-120b
18.7
WeirdML
gpt-oss-120b leads by +2.8
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Haiku 4.5
45.4
gpt-oss-120b
48.2
Full benchmark table
| Benchmark | Claude Haiku 4.5 | gpt-oss-120b |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 8.9 | 4.4 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 3.2 | 15.8 |
Dtbench | 56.0 | 60.5 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 61.6 | 67.7 |
Lmca | 36.4 | 26.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 66.6 | 88.9 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 13.2 | 13.9 |
Terminal Bench Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence. | 35.5 | 18.7 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 45.4 | 48.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.00 | $5.00 | 200K tokens (~100 books) | $20.00 | |
| $0.04 | $0.17 | 131K tokens (~66 books) | $0.70 |
People also compared