Gemini 4 Argon vs GPT-6 Sol
| Gemini 4 Argon | GPT-6 Sol | |
|---|---|---|
| Announced | ||
| Released | ||
| Input / 1M tokens | $2$4 from 1 Dec 2026 | $2 |
| Cached input / 1M tokens | $0.10$0.20 from 1 Dec 2026 | $0.20 |
| Output / 1M tokens | $10$20 from 1 Dec 2026 | $10 |
| Context window | 1M | 1.05M |
| Output limit | 65K | 128K |
| Benchmarks | ||
| AutomationBench 1.0.6 Private set | 51.3%1 | 33.2%2 |
| OSWorld 2.0 (v2026.08.08) Offline set, partial score | 69.2%3 | 60.5%4 |
| DeepSWE v1.1 | 77.9% | 68.8%5 |
| Gemini 4 Argon | GPT-6 Sol | |
|---|---|---|
| Other benchmarks | ||
| Terminal-Bench 4.0 | 57.4% | No data |
| Terminal-Bench Science 0.1 | 57.6% | No data |
| OSWorld 2.1 Offline set (82 tasks), partial score | 74.7%6 | No data |
| FrontierSWE v2 | 55.0%7 | No data |
| Chartography No tools | 71.6%8 | No data |
| SEC-bench Pro 260505 | 83.4%9 | No data |
| Agents' Last Exam v1 Pass rate, set not stated | 39.5%10 | No data |
| Agents' Last Exam v1 Measure and set not stated | No data | 56.4%11 |
| Agents' Last Exam v1.1 Score, all tasks (122) | 69.0%12 | No data |
| GraphWalks BFS, up to 128K | 99.7%13 | No data |
| GraphWalks BFS, 256K + 1M problems | 84.2% | No data |
Notes
- AutomationBench 1.0.6, Private set, Gemini 4 Argon: Run by Zapier · set named in the evaluation methodology the post cites
- AutomationBench 1.0.6, Private set, GPT-6 Sol: Run by Zapier · xhigh effort
- OSWorld 2.0 (v2026.08.08), Offline set, partial score, Gemini 4 Argon: Gemini CUA harness · max of 3 runs, one attempt per run
- OSWorld 2.0 (v2026.08.08), Offline set, partial score, GPT-6 Sol: xhigh effort
- DeepSWE v1.1, GPT-6 Sol: max effort
- OSWorld 2.1, Offline set (82 tasks), partial score, Gemini 4 Argon: Gemini CUA harness · highest thinking · max of 3 runs, one attempt per run
- FrontierSWE v2, Gemini 4 Argon: Run by Proximal · Proximal's public leaderboard
- Chartography, No tools, Gemini 4 Argon: Run by Surge AI · Surge AI's public leaderboard
- SEC-bench Pro 260505, Gemini 4 Argon: Antigravity harness · pass@1, mean of 3 attempts · 183-task JavaScript engine split (May 2026) · LLM judge for crashes in both builds
- Agents' Last Exam v1, Pass rate, set not stated, Gemini 4 Argon: ALE-Claw harness · 5-hour window · safety filters on
- Agents' Last Exam v1, Measure and set not stated, GPT-6 Sol: harness not stated · max effort
- Agents' Last Exam v1.1, Score, all tasks (122), Gemini 4 Argon: ALE-Claw harness · 5-hour window · October 17, 2026 task files · safety filters on
- GraphWalks, BFS, up to 128K, Gemini 4 Argon: 650 problems up to 128K tokens, per the model evaluation document