GPT-5.1 Benchmark Details
GPT-5.1 currently shows benchmark results led by MMMU (2 / 28, score 85.40), Terminal Bench Hard (2 / 13, score 43), FrontierMath (13 / 60, score 26.70). This page also compares it with 2 competitor models and 2 predecessor or same-series models, including performance and pricing views when available. 2 source links are attached for reference.
Benchmark Results
Benchmark Results
General Knowledge
13 evaluationsCoding and Software Engineer
8 evaluationsMath and Reasoning
5 evaluationsMultimodal Understanding
3 evaluationsAgent Level Benchmark
2 evaluationsAI Agent - Tool Usage
2 evaluationsCompetitor Comparison
Benchmark scores for GPT-5.1 compared against top models in its class
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GPT-5.1Current | Claude Opus 4 | Gemini 2.5-Pro |
|---|---|---|---|
ARC-AGI 综合评估 | 72.80Thinking Level · High | 35.70Standard Mode | 37.00Thinking Enabled |
ARC-AGI-2 综合评估 | 17.60Thinking Level · High | 8.60Standard Mode | 4.90Thinking Enabled |
HLE 综合评估 | 42.70Thinking Level · High ｜ Tools | 10.70Standard Mode | 21.60Thinking Enabled |
LiveBench 综合评估 | 72.04Thinking Level · High | -- | 58.33Thinking Level · High |
GPQA Diamond 科学与综合推理 | 88.10Thinking Level · High | 79.60Standard Mode | 86.40Thinking Enabled |
GSO 编程与软件工程 | 13.70Thinking Level · High ｜ Tools | -- | 3.92Standard Mode ｜ Tools |
SWE-bench Verified 编程与软件工程 | 76.30Thinking Level · High ｜ Tools | 72.50Standard Mode | 67.20Thinking Enabled |
AIME2025 数学推理 | 94.00Thinking Level · High | 75.50Standard Mode | 88.00Thinking Enabled |
FrontierMath 数学推理 | 26.70Thinking Level · High ｜ Tools | 4.50Standard Mode | 11.00Standard Mode |
12.50Thinking Level · High ｜ Tools | 4.2032K | 2.10Standard Mode | |
MMMU 多模态理解 | 85.40Thinking Level · High | -- | 82.00Thinking Enabled |
VPCT 多模态理解 | 58.70Thinking Level · High | -- | 46.40Standard Mode |
Standard API Pricing: GPT-5.1 vs. Peer Models
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
When a context threshold exists, the charted base price only applies within these limits:
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
GPT-5.1 | OpenAI | $1.25 / 1M tokens | $10 / 1M tokens | — |
Claude Opus 4 | Anthropic | $15 / 1M tokens | $75 / 1M tokens | — |
Gemini 2.5-Pro | Google Deep Mind | $1.25 / 1M tokens | $10 / 1M tokens | <= 200000 |
Version History
How each version of the GPT-5.1 series stacks up on benchmark tests
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.
| Benchmark | GPT-5.1Current | GPT-5 | GPT-4.5 |
|---|---|---|---|
ARC-AGI 综合评估 | 72.80Thinking Level · High | 65.70Thinking Level · High | -- |
ARC-AGI-2 综合评估 | 17.60Thinking Level · High | 9.90Thinking Level · High | -- |
HLE 综合评估 | 42.70Thinking Level · High ｜ Tools | 35.20Thinking Enabled ｜ Tools | -- |
GPQA Diamond 科学与综合推理 | 88.10Thinking Level · High | 87.30Thinking Enabled ｜ Tools | 71.40Standard Mode |
GSO 编程与软件工程 | 13.70Thinking Level · High ｜ Tools | 6.90Thinking Level · High ｜ Tools | -- |
IC SWE-Lancer(Diamond) 编程与软件工程 | 69.70Thinking Level · High | -- | 32.60Standard Mode |
SWE-Bench Pro - Public 编程与软件工程 | 50.80Thinking Level · High | 36.30Thinking Level · High | -- |
SWE-bench Verified 编程与软件工程 | 76.30Thinking Level · High ｜ Tools | 72.80Thinking Level · High | 38.00Standard Mode |
Text Arena (Coding) 编程与软件工程 | 1387.00Thinking Level · Medium | 1395.00Thinking Level · Medium | -- |
WeirdML v2 编程与软件工程 | 60.77Thinking Level · High ｜ Tools | 60.70Thinking Level · High ｜ Tools | -- |
AIME2025 数学推理 | 94.00Thinking Level · High | 99.60Thinking Enabled ｜ Tools | -- |
FrontierMath 数学推理 | 26.70Thinking Level · High ｜ Tools | 26.30Thinking Level · High ｜ Tools | -- |
Single-Benchmark Version Trend
Viewing: ARC-AGI · 综合评估
Standard API Pricing Across the GPT-5.1 Series
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
GPT-5.1 | OpenAI | $1.25 / 1M tokens | $10 / 1M tokens | — |
GPT-5 | OpenAI | $1.25 / 1M tokens | $10 / 1M tokens | — |