BlogLLM Benchmark Scores as Published, Side by Side
GPT-5.1: Benchmark Scores as Published
Every result the catalog holds for GPT-5.1: 50 tests in 12 areas, from 7 pages. 44 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 2025-11-12Context 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 (wins or ties) | 38.8% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high |
| Vals Finance Agent (version not stated) | 56.6% | Anthropic, Claude Opus 4.6checked 2026-10-15 | - |
| Investment Banking Modeling Tasks (Internal) | 59.1% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high |
| GDPval (no ties) | 37.1% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high |
| GDPval (ties allowed, clear wins) | 35.5% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high |
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-bench Verified | 76.3% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 3 more pages | Effort: high; Harness: harness with JSON-based apply_patch tool; Dataset revision: all 500 problems |
| SWE-Bench Pro | 50.8% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: high |
| Terminal-Bench 2.0 | 47.6% | Anthropic, Claude Opus 4.5checked 2026-10-15; printed on 1 more page | - |
| 48.6% | Anthropic, Claude Opus 4.5checked 2026-10-15 | Harness: Terminus-2 in the Anthropic improved hosting environment | |
| Terminal-Bench Hard | 43% | Z.ai, GLM-4.7 model cardchecked 2026-10-15 | Effort: high |
| SWE-Lancer IC Diamond | 69.7% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Dataset revision: 197 of 237 IC Diamond problems (40 omitted) |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 88.1% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 3 more pages | Effort: high; Tools: none |
| AIME 2025 | 94% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 2 more pages | Effort: high; Tools: none |
| HMMT February 2025 | 96.3% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: high; Tools: none |
| FrontierMath Tier 1-3 | 26.7% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 1 more page | Effort: high; Tools: python |
| FrontierMath Tier 4 | 12.5% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Tools: python |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GraphWalks BFS up to 128k (F1) | 76.8% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Context: <128k |
| MRCR v2 8-needle 128K-256K | 29.6% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Context: 128k-256k |
| MRCR v2 8-needle 64K-128K | 36% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Context: 64k-128k |
| GraphWalks parents up to 128k (accuracy) | 71.5% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Context: <128k |
| MRCR v2 8-needle 16K-32K | 44% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Context: 16k-32k |
| MRCR v2 8-needle 32K-64K | 37.8% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Context: 32k-64k |
| MRCR v2 8-needle 4K-8K | 65.3% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Context: 4k-8k |
| MRCR v2 8-needle 8K-16K | 47.8% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Context: 8k-16k |
| BrowseComp Long Context 128k | 90% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 1 more page | Effort: high; Context: 128k |
| BrowseComp Long Context 256k | 89.5% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Context: 256k |
Computer Use
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| ScreenSpot-Pro (with tools) | 64.2% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Tools: python |
Multimodal Understanding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CharXiv Reasoning (no tools) | 67% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Tools: none |
| MMMU (validation) | 85.4% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 1 more page | Effort: high |
| CharXiv Reasoning (with tools) | 80.3% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Tools: python |
| MMMU-Pro (with tools) | 79% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Tools: python |
| Video-MMMU | 82.9% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Tools: none |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 25.7% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: high; Tools: none |
| MMLU-Pro | 87% | Z.ai, GLM-4.7 model cardchecked 2026-10-15 | Effort: high |
| Humanity's Last Exam (with tools) | 42.7% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: high; Tools: search, python |
| ARC-AGI-2 | 17.6% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: high |
| ARC-AGI-1 | 72.8% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high |
| ChatGPT answers without errors (no search) | 87.3% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Tools: none |
| ChatGPT answers without errors (with search) | 91.2% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Tools: search |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LiveCodeBench v6 | 87% | Z.ai, GLM-4.7 model cardchecked 2026-10-15 | Effort: high |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Toolathlon | 36.1% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high |
| τ²-bench Telecom | 95.6% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 1 more page | Effort: high |
| MCP Atlas | 44.5% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high |
| τ²-bench Retail | 77.9% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 1 more page | Effort: high |
| τ²-bench Airline | 67% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15 | Effort: high |
| τ²-bench (domain not stated) | 82.7% | Z.ai, GLM-4.7 model cardchecked 2026-10-15 | Effort: high |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| BrowseComp | 50.8% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: high |
Multilingual
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMMLU | 89.5% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: high |
Safety and Alignment
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Sensitive conversations (emotional reliance) | 0.785 | OpenAI, Introducing GPT-5.2checked 2026-10-15 | - |
| Sensitive conversations (mental health) | 0.684 | OpenAI, Introducing GPT-5.2checked 2026-10-15 | - |
| Sensitive conversations (self-harm) | 0.937 | OpenAI, Introducing GPT-5.2checked 2026-10-15 | - |
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 | $1.25 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Cached input | $0.125 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output | $10 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Input, batch | $0.625 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Cached input, batch | $0.0625 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output, batch | $5 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Input, flex | $0.625 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Cached input, flex | $0.0625 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output, flex | $5 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Input, fast | $2.5 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Cached input, fast | $0.25 | OpenAI, OpenAI API pricingchecked 2026-10-15 | - |
| Output, fast | $20 | 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 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.