Reasoning
198-question Diamond subset; independent AA evaluation
- 01
- 02
- 03
- 03
- 03
- 08
GPT-5.5
Across the task benchmarks we track, GPT-5.5’s strongest relative results are in reasoning, coding, and knowledge work. On GPQA Diamond, it scores 93.5%, ranking joint #8 among 30 models with reported results in our dataset.
Updated: Data as of:
Strongest results
| Benchmark | Measures | Score |
|---|---|---|
| GPQA ↗Diamond / Artificial Analysis | Reasoning | 93.54%Joint #8 of 30 |
| Humanity's Last Exam ↗Stable HLE — text-only subset | Expert reasoning | 45.8%#19 of 68 |
| GDP.pdf ↗100 tasks / All-pass / five attempts | Professional document reasoning | 22.6%#18 of 55 |
| Terminal-Bench ↗4.0 / mini-swe-agent | Working in a terminal | 14.65%Joint #27 of 56 |
Model details
| Model | GPT-5.5 |
|---|---|
| Agent Index v1.2 | Insufficient coverage (3/7) · Preview |
| Creator | OpenAI (opens in a new tab) |
| Availability | Proprietary |
| Context size | 922,000 tokens (opens in a new tab) |
| Max output | 128,000 tokens (opens in a new tab) |
| Knowledge cutoff | Not reported |
| License | Not reported |
Pricing and performance
Per provider and reported configuration. Prices are USD per 1M tokens.
| Provider / configuration | Contexttokens | InputUSD / 1M tokens | OutputUSD / 1M tokens | LatencyTTFT · seconds | Speedtokens / sec |
|---|---|---|---|---|---|
| GPT-5.5 (xhigh) | 272,000 | $5.50 (opens in a new tab) | $33.00 (opens in a new tab) | 51.632 (opens in a new tab) | 142.511 (opens in a new tab) |
| GPT-5.5 (xhigh) | 1,050,000 | $5.00 (opens in a new tab) | $30.00 (opens in a new tab) | 80.223 (opens in a new tab) | 95.007 (opens in a new tab) |
Benchmark performance
GPT-5.5 in color, alongside leading models. Latest stored reports, best effort per report date.
GPQA Diamond ↗
Coding
113 tasks; mini-swe-agent
- 01
- 01
- 01
- 04
- 05
- 08
Work Automations
Private held-out set; API mode; 50 steps; strict pass/fail
- 01
- 02
- 03
- 04
- 05
- 14
Knowledge Work
220 tasks; Stirrup agent; pairwise Elo
- 01
- 02
- 03
- 04
- 05
- 27
Reported benchmarks
All published results in our dataset, with versions, evaluation settings, and sources.
| Benchmark | Score | Evaluation setup | Source |
|---|---|---|---|
| AA-Briefcase1.1 / combined EloCombined Elo · Higher is better | 1,136 Elo | selection: best reported configuration per release · GPT-5.5 (xhigh) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 1.07% | GPT-5.5; private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 2.59% | GPT-5.5 (Low); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 8.98% | GPT-5.5 (Medium); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 12.79% | GPT-5.5 (High); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 16.59% | GPT-5.5 (XHigh); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better | 47.3% | reported precision decimals: 1 · result quality: reported · GPT-5.5 (xhigh); private held-out 657 tasks; 50 turns; objective completion with zero credit for any guardrail violation. · source model href: /models/gpt-5-5 · task count: 657 · Tools enabled · turn cap: 50 | Artificial Analysis (opens in a new tab)independent |
| DeepSWEv1.1Pass@1 · Higher is better | 67% | mini-swe-agent; effort=xhigh; ±6 percentage points | Datacurve ↗ (opens in a new tab)benchmark publisher |
| Gaia2CLI · OpenClaw 2026.4.1Pass@1 · Higher is better | 56.4% | api host: openai · capabilities: search, execution, adaptability, ambiguity, time · edition: Gaia2-CLI · harness: OpenClaw 2026.4.1 · reasoning: xhigh · reasoning context: Not specified | Meta Agents Research Environments ↗ (opens in a new tab)benchmark publisher · 2026-05-15 |
| GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better | 22.6% | selection: best reported configuration per release · GPT-5.5 (high) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,053.07 Elo | GPT-5.5 (Low); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,335.86 Elo | GPT-5.5 (High); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 977.8 Elo | GPT-5.5 (Non-reasoning); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,242.99 Elo | GPT-5.5 (Medium); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,359.24 Elo | GPT-5.5 (Xhigh); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 91.01% | GPT-5.5 (Low); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 93.232% | GPT-5.5 (High); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 76.768% | GPT-5.5 (Non-reasoning); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 92.626% | GPT-5.5 (Medium); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 93.535% | GPT-5.5 (Xhigh); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 52.2% | Launch comparison; GPT models evaluated at xhigh effort; research environment. Competitor settings follow source footnotes. · subset: full · Tools enabled | OpenAI ↗ (opens in a new tab)provider reported · 2026-04-23 |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 41.4% | Launch comparison; GPT models evaluated at xhigh effort; research environment. Competitor settings follow source footnotes. · subset: full · No tools | OpenAI ↗ (opens in a new tab)provider reported · 2026-04-23 |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 45.8% | question count: 2158 · reported precision decimals: 1 · GPT-5.5 (xhigh); original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/gpt-5-5 · subset: text · No tools | Artificial Analysis (opens in a new tab)independent |
| IFBench58 constraint typesAccuracy · Higher is better | 75.9% | selection: publisher default displayed configuration · GPT-5.5 (xhigh) | Artificial Analysis (opens in a new tab)independent |
| LifeValNovember 2026Unweighted average reward · Higher is better | 77.4% | aggregation: Average attempts within each task, then average all 169 task means equally. No willingness-to-pay weighting. Reward multiplied by 100; published display values rounded to one decimal place. · Effort not specified in chart · tasks: 169 | OpenAI ↗ (opens in a new tab)benchmark publisher · 2026-11-02 |
| MCP-AtlasApril 2026 / public 500Task success · Higher is better | 79.4% | xhigh; public 500; 100 tool calls | Scale AI ↗ (opens in a new tab)benchmark publisher |
| MyPCBench184 tasks · 100 stepsPerfect-task rate · Higher is better | 45.1% | interface: computer + bash · judge: gemini-3.1-flash-lite-preview · max steps: 100 · rubric score percent: 83.6 · selection: Canonical matched-protocol rows only; four 200-step self-reported rows retained in source snapshot, excluded from this track. · tasks: 184 | MyPCBench / Carnegie Mellon University ↗ (opens in a new tab)benchmark publisher |
| Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better | 14.646% | harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · GPT-5.5 (Xhigh) | Artificial Analysis (opens in a new tab)independent |