BlogLLM Benchmark Scores as Published, Side by Side
GPT-5.4 mini: Benchmark Scores as Published
Every result the catalog holds for GPT-5.4 mini: 20 tests in 8 areas, from 3 pages. 16 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 2026-03-17Context window 400KMax output 128KInput Text, imageOutput TextWeights ClosedData version 2026103001, as of 2026-10-30
Knowledge Work
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GDPval-AA v2 | 1171 | Google, Gemini 3.5 Flash-Lite model cardchecked 2026-10-15 | - |
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-Bench Pro | 54.4% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15; printed on 1 more page | Effort: xhigh |
| Terminal-Bench 2.1 | 59.2% | Google, Gemini 3.5 Flash-Lite model cardchecked 2026-10-15 | Harness: Terminus-2 |
| Terminal-Bench 2.0 | 60% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 88% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MRCR v2 8-needle 128K | 42.7% | Google, Gemini 3.5 Flash-Lite model cardchecked 2026-10-15 | Context: 128k (average) |
| GraphWalks BFS up to 128k (F1) | 76.3% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Context: 0K-128K |
| MRCR v2 8-needle 128K-256K | 33.6% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Context: 128K-256K |
| MRCR v2 8-needle 64K-128K | 47.7% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Context: 64K-128K |
| GraphWalks parents up to 128k (accuracy) | 71.5% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Context: 0-128K |
Computer Use
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| OSWorld-Verified | 72.1% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15; printed on 1 more page | Effort: xhigh |
Multimodal Understanding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CharXiv Reasoning (no tools) | 80.3% | Google, Gemini 3.5 Flash-Lite model cardchecked 2026-10-15 | Tools: none |
| MMMU-Pro | 76.6% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh |
| MMMU-Pro (with tools) | 78% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Tools: python |
| OmniDocBench 1.5 (overall edit distance)lower is better | 0.1263 | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: none; Tools: none |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 28.2% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Tools: none |
| Humanity's Last Exam (with tools) | 41.5% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Tools: with tools |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Toolathlon | 42.9% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh |
| τ²-bench Telecom | 93.4% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh |
| MCP Atlas | 57.7% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh |
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 | $0.75 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Cached input | $0.075 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output | $4.5 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Input, batch | $0.375 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Cached input, batch | $0.0375 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output, batch | $2.25 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Input, flex | $0.375 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Cached input, flex | $0.0375 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output, flex | $2.25 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Input, fast | $1.5 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Cached input, fast | $0.15 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output, fast | $9 | 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 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-4o
- 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.