GPT-6.1 Sol
OpenAI·7 个数据来源·更新于 2026-11-10
评测表现
只在同一来源、同一口径下比较。切换来源可查看不同测试结果。
综合分数和同榜图表来自 LLM Stats 榜单(采集于 2026-11-10);下方逐项成绩来自模型页。榜单出处
同榜模型表现
LLM Stats Score · 同一来源与榜单口径,分数越高越好
查看完整对比数据
| 模型与配置 | LLM Stats Score | 每任务成本 |
|---|---|---|
| Kimi K3.1 Pro | 55.1 | 未公布 |
| Claude Mythos Preview | 53.9 | 未公布 |
| Gemini 4 Argon | 53.8 | 未公布 |
| GPT-6.1 Sol · 当前模型 | 53.1 | 未公布 |
| Claude Opus 5 | 53 | 未公布 |
| Muse Wonder Full | 52.8 | 未公布 |
| Claude Fable 5 | 52.4 | 未公布 |
不同来源的分数不能直接相加或横向比较;评测任务成本不是 API Token 单价。
逐项基准成绩
18 项已收录成绩 · 保留原始单位和测试条件
Third-party Mercor APEX-Agents. Pass@1 overall 60.0% at Max. MC 58.4% / IB 58.1% Max; Pass@1 ±5.6. Single overall row only (no separate MC/IB bench IDs).
成绩出处AutomationBench 1.0.6. OpenAI GPT-6.1 Sol launch interactive chart. Highest published score across the reported effort sweep: max effort (0.361). Other efforts: low 0.247, medium 0.317, high 0.332, xhigh 0.355. Evaluations used OpenAI research environments or API and may differ from production ChatGPT.
成绩出处DeepSWE v1.1. OpenAI GPT-6.1 Sol launch interactive chart. Highest published score across the reported effort sweep: high effort (0.7522). Other efforts: low 0.6438, medium 0.7301, xhigh 0.719, max 0.719. Evaluations used OpenAI research environments or API and may differ from production ChatGPT.
成绩出处Third-party Cognition / Epoch. FrontierCode 1.1 Main at medium reasoning effort (50.2%). Extended stored separately as frontiercode-1.1-extended.
成绩出处Third-party Cognition / Devin. FrontierCode 1.1 Extended (60.4%). Main stored separately as frontiercode-1.1 (medium 50.2%).
成绩出处Third-party Epoch AI Benchmarking Hub. FrontierMath Tier 4 (v2) at max reasoning effort (100%).
成绩出处gdp.pdf. OpenAI GPT-6.1 Sol launch interactive chart. Highest published score across the reported effort sweep: high effort (0.32). Other efforts: low 0.27, medium 0.30, xhigh 0.318, max 0.31. Evaluations used OpenAI research environments or API and may differ from production ChatGPT.
成绩出处HealthBench, length-adjusted score (unadjusted 0.567). GPT-6.1 Sol system card addendum Table 7.
成绩出处HealthBench Consensus, length-adjusted score (unadjusted 0.959). GPT-6.1 Sol system card addendum Table 7.
成绩出处HealthBench Hard, length-adjusted score (unadjusted 0.334). GPT-6.1 Sol system card addendum Table 7.
成绩出处HealthBench Professional, length-adjusted score (unadjusted 0.672). GPT-6.1 Sol system card addendum Table 7.
成绩出处Third-party Artificial Analysis AA HLE text-only (2,158 questions, no tools) at max reasoning effort (52.9%).
成绩出处Strict pass rate on 55 regulatory-affairs tasks. Plain API via Vercel AI Gateway with a web_search tool (Exa), provider default settings, one answer per task, graded by GPT-6.1 Sol at medium reasoning effort (Arca, 4 Nov 2026 edition).
成绩出处MentalHealthBench overall at max reasoning effort (0.579). Acuity splits at max effort: non-acute 0.573, high acuity 0.591, emergent 0.580. GPT-6.1 Sol system card addendum Table 9.
成绩出处Third-party Artificial Analysis (AA). MMMU-Pro at max reasoning effort (85.95%).
成绩出处OSWorld 2.0 offline set, partial reward (v2026.08.08), not strict completion or the full task set. OpenAI GPT-6.1 Sol launch interactive chart. Highest published score across the reported effort sweep: max effort (0.7142). Other efforts: low 0.5896, medium 0.6684, high 0.6956, xhigh 0.6938. Evaluations used OpenAI research environments or API and may differ from production ChatGPT.
成绩出处Third-party Epoch AI Benchmarking Hub. SimpleQA Verified at max reasoning effort (73.9%).
成绩出处Terminal-Bench Science 0.1. OpenAI GPT-6.1 Sol launch interactive chart. Highest published score across the reported effort sweep: max effort (0.5702). Other efforts: low 0.4371, medium 0.4756, high 0.5114, xhigh 0.5371. Evaluations used OpenAI research environments or API and may differ from production ChatGPT.
成绩出处技术规格
只展示有可靠来源的资料;优先采用厂商官网与官方模型仓库。
- 发布日期
- 2026-09-29LLM Stats
- 知识截止
- 2026-04-30厂商官网
- 上下文窗口
- 1.05M Token厂商官网
- 最大输入
- 1.05M TokenLLM Stats
- 最大输出
- 128K Token厂商官网
- 输入模态
- 文本、图像厂商官网
- 输出模态
- 文本厂商官网
- 开放权重
- 否Artificial Analysis
- 推理模式
- 支持Artificial Analysis
- 许可证
- ProprietaryLLM Stats
价格与用量
美元 / 百万 Token。不同服务商或测试配置的报价分别列出。
| 来源 / 服务商 | 输入 | 输出 | 缓存读取 |
|---|---|---|---|
| 厂商官网 · Explore models and compare capabilities | $2 | $10 | $0.1 |
| OpenAI | $2 | $10 | $0.1 |
每个数字,都有出处
同名模型通过开发机构和明确版本关联。预览版、日期版本和不同规模模型分别建档。
厂商官网
厂商官方文档 · 基础规格与标准 API 报价
Artificial Analysis
公开评测数据;保留来源原始口径
LLM Stats
公开模型页与公开榜单;自报成绩单独标识
BenchLM
公开评测数据;保留来源原始口径
Arena
Arena 官方公开数据集 · CC BY 4.0
LiveBench
公开评测数据;保留来源原始口径
OpenRouter
公开模型目录与 API 报价
查看全部配置与采集记录
| 来源 / 配置 | 采集时间 | 原始数据 |
|---|---|---|
| Artificial AnalysisGPT-6.1 Sol (max)SHA-256 c969b09538b1254d… | 2026-11-10T14:08:35Z | 查看来源 |
| Artificial AnalysisGPT-6.1 Sol (xhigh)SHA-256 c969b09538b1254d… | 2026-11-10T14:08:35Z | 查看来源 |
| Artificial AnalysisGPT-6.1 Sol (high)SHA-256 c969b09538b1254d… | 2026-11-10T14:08:35Z | 查看来源 |
| Artificial AnalysisGPT-6.1 Sol (medium)SHA-256 c969b09538b1254d… | 2026-11-10T14:08:35Z | 查看来源 |
| Artificial AnalysisGPT-6.1 Sol (low)SHA-256 c969b09538b1254d… | 2026-11-10T14:08:35Z | 查看来源 |
| Artificial AnalysisGPT-6.1 Sol (Max)SHA-256 d88cf30c17a50945… | 2026-11-10T13:51:48Z | 查看来源 |
| Artificial AnalysisGPT-6.1 Sol (High)SHA-256 d88cf30c17a50945… | 2026-11-10T13:51:48Z | 查看来源 |
| Artificial AnalysisGPT-6.1 Sol (Low)SHA-256 d88cf30c17a50945… | 2026-11-10T13:51:48Z | 查看来源 |
| Artificial AnalysisGPT-6.1 Sol (Medium)SHA-256 d88cf30c17a50945… | 2026-11-10T13:51:48Z | 查看来源 |
| Artificial AnalysisGPT-6.1 Sol (Xhigh)SHA-256 d88cf30c17a50945… | 2026-11-10T13:51:48Z | 查看来源 |
| LLM StatsGPT-6.1 Sol | 2026-11-10T14:08:28Z | 查看来源 |
| LLM StatsGPT-6.1 SolSHA-256 8c8c3ecddc3a9ff1… | 2026-11-10T13:52:09Z | 查看来源 |
| BenchLMGPT-6.1 Sol | 2026-11-10 | 查看来源 |
| ArenaGPT-6.1 Sol (Max) | 2026-11-10T14:07:52Z | 查看来源 |
| ArenaGPT-6.1 Sol (Max) | 2026-11-10T14:07:52Z | 查看来源 |
| ArenaGPT-6.1 Sol (Max) | 2026-11-10T14:07:52Z | 查看来源 |
| ArenaGPT-6.1 Sol (Max) | 2026-11-10T14:07:52Z | 查看来源 |
| LiveBenchGPT-6.1 Sol | 2026-11-10T14:08:34Z | 查看来源 |
| OpenRouterGPT-6.1 SolSHA-256 63cbc45064d84060… | 2026-11-10T13:51:49Z | 查看来源 |
| 厂商官网Explore models and compare capabilitiesSHA-256 c7a891dfc83f874b… | 2026-11-10T13:59:32Z | 查看来源 |