BlogLLM Benchmark Scores as Published, Side by Side
GPT-4o: Benchmark Scores as Published
Every result the catalog holds for GPT-4o: 47 tests in 14 areas, from 4 pages. 19 printed by OpenAI itself, the rest by the company named beside each number. Each number is as printed; nothing is ranked or rescored.
Developer OpenAIReleased 2024-05-13Context window 128KMax output 16.4KInput Text, imageOutput TextWeights ClosedData version 2026103001, as of 2026-10-30
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-bench Verified | 30.8% | OpenAI, Introducing GPT-5checked 2026-10-15; printed on 1 more page | - |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 70.1% | OpenAI, Introducing GPT-5checked 2026-10-15; printed on 2 more pages | Tools: no tools |
| AIME 2025 | 42.1% | OpenAI, Introducing GPT-5checked 2026-10-15 | Tools: python |
| AIME 2024 | 9.3% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | Model as printed: GPT-4o-0513 |
| 9.3% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | Model as printed: GPT-4o 0513 | |
| MATH-500 | 74.6% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15; printed on 1 more page | Model as printed: GPT-4o 0513 |
| 74.6% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | Model as printed: GPT-4o-0513 | |
| CNMO 2024 | 10.8% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| AIME 2024 cons@64 (majority vote over 64 samples) | 13.4% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| RULER at 128K | 88.9% | Mistral AI, Medium is the new largechecked 2026-10-15 | Context: 128000 |
| RULER at 32K | 96% | Mistral AI, Medium is the new largechecked 2026-10-15 | Context: 32000 |
Multimodal Understanding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CharXiv Reasoning (no tools) | 58.8% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| MMMU-Pro | 59.9% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| MMMU (validation) | 72.2% | OpenAI, Introducing GPT-5checked 2026-10-15; printed on 1 more page | - |
| AI2D (test) | 93.3% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| Video-MMMU | 61.2% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| ERQA | 35.2% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| ChartQA | 86% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| DocVQA (ANLS) | 85.9 | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 5.3% | OpenAI, Introducing GPT-5checked 2026-10-15 | Tools: no tools |
| MMLU-Pro | 72.6% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15; printed on 1 more page | - |
| MMLU-Redux | 88% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| C-Eval | 76% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| MMLU | 87.2% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| SimpleQA | 38.2% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | Tools: none |
| DROP (F1) | 83.7% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| Chinese SimpleQA | 58.7% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LiveCodeBench v6 | 31.4% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| Codeforces rating | 759 | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | Model as printed: GPT-4o 0513 |
| 759 | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | Model as printed: GPT-4o-0513 | |
| LiveCodeBench (version not stated) | 32.9% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | Model as printed: GPT-4o-0513 |
| 34.2% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | Model as printed: GPT-4o 0513 | |
| Aider polyglot | 25.8% | OpenAI, Introducing GPT-5checked 2026-10-15; printed on 1 more page | - |
| MultiPL-E | 79.8% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| HumanEval | 91.5% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| Codeforces percentile | 23.6% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| τ²-bench Telecom | 23.5% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| τ²-bench Retail | 63.4% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| τ²-bench Airline | 45.5% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| FRAMES | 80.5% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
Instruction Following
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MultiChallenge | 40.3% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| IFEval | 87.2% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| COLLIE | 61% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| IFEval (prompt-level strict) | 84.3% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
Multilingual
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CLUEWSC | 87.9% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
Writing and Conversation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AlpacaEval 2.0 (length-controlled win rate) | 51.1% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
Healthcare
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| HealthBench | 32 | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| HealthBench Hard | 0 | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
| HealthBench Hard (hallucination rate)lower is better | 15.8% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
Safety and Alignment
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| OpenAI deception evals (deception rate)lower is better | 20.6% | OpenAI, Introducing GPT-5checked 2026-10-15 | - |
Preference and Composite Rankings
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Arena-Hard win rate (GPT-4-1106 judge) | 80.4% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15; printed on 1 more page | - |
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 | $2.5 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Cached input | $1.25 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output | $10 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Input, batch | $1.25 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output, batch | $5 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Input, fast | $4.25 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Cached input, fast | $2.125 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output, fast | $17 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
More from OpenAI
- GPT-6.1 Terra
- GPT-6.1 Sol
- GPT-6 Luna
- GPT-6 Sol
- GPT-6 Astra
- GPT-5.6 Luna
- GPT-5.6 Sol
- GPT-5.6 Terra
- GPT-5.5
- GPT-5.5 Pro
- GPT-5.4 mini
- GPT-5.4 nano
- GPT-5.4
- GPT-5.4 Pro
- GPT-5.3-Codex
- GPT-5.2-Codex
- GPT-5.2
- GPT-5.2 Instant
- GPT-5.2 Pro
- GPT-5.1-Codex-Max
- GPT-5.1
- GPT-5.1 Instant
- GPT-5-Codex
- GPT-5
- GPT-5 mini
- GPT-5 Pro
- gpt-oss-120b
- gpt-oss-20b
- ChatGPT agent
- codex-1
- o3
- OpenAI o4-mini
- GPT-4.1
- GPT-4.5
- Deep research
- o3-mini
- o1
- o1-mini
- GPT-5.5 Instant
- gpt-5.6-cyber
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.