Gemini 4 Argon vs Gemini 4 Neon
| Gemini 4 Argon | Gemini 4 Neon | |
|---|---|---|
| Announced | ||
| Released | ||
| Lineup | Carbon = Argon › Neon › Hydrogen | Carbon = Argon › Neon › Hydrogen |
| Input / 1M tokens | $2$4 from 1 Dec 2026 | $3 |
| Cached input / 1M tokens | $0.10$0.20 from 1 Dec 2026 | $0.15 |
| Output / 1M tokens | $10$20 from 1 Dec 2026 | $15 |
| Context window | 1M | 1M |
| Output limit | 65K | 65K |
| Benchmarks | ||
| Terminal-Bench Science 0.1 | 57.6% | 70.5%1 |
| AutomationBench, release not specified Private set | 51.3%2 | 56.3%3 |
| FrontierCode 2.0 Score, all tasks (132) | 27.6%4 | 46.2%5 |
| FrontierCode 2.0 Pass rate, all tasks (132) | 30.6%6Devin CLI | 50.8%7Antigravity CLI |
| Chartography No tools | 71.6%8 | 73.5%9 |
| SEC-bench Pro 260505 | 83.4%10 | 90.5%11 |
| Agents' Last Exam v1.1 Score, all tasks (122) | 69.0%12ALE-Claw | 75.8%13Antigravity |
| GraphWalks BFS, 256K + 1M problems | 84.2% | 95.2%14 |
| ExploitGym Mitigations off, score | 42.0%15 | 48.3%16 |
| Gemini 4 Argon | Gemini 4 Neon | |
|---|---|---|
| Other benchmarks | ||
| HLE-Diamond No tools | No data | 71.3%17 |
| SWE-bench Pro V2 Full set (642 tasks) | 99.22%18 | No data |
| SWE-bench Pro V2 HARD-51 (51 tasks) | 92.16%19 | No data |
| Terminal-Bench 4.0 | 57.4% | No data |
| Terminal-Bench 4.1 | 55.5%20 | No data |
| OSWorld 2.1 Offline set (82 tasks), partial score | 74.7%21 | No data |
| OSWorld 2.0 (v2026.08.08) Offline set, partial score | 69.2%22 | No data |
| FrontierSWE v2 | 55.0%23 | No data |
| DeepSWE v1.1 | 77.9% | No data |
| Agents' Last Exam v1 Pass rate, set not specified | 39.5%24 | No data |
| GraphWalks BFS, up to 128K | 99.7%25 | No data |
Notes
- Terminal-Bench Science 0.1, Gemini 4 Neon: mini-swe-agent vision harness · highest thinking · average of 5 attempts per task
- AutomationBench, release not specified, Private set, Gemini 4 Argon: Run by Zapier · set named in the evaluation methodology the post cites
- AutomationBench, release not specified, Private set, Gemini 4 Neon: Run by Zapier · set of the official public leaderboard the evaluation methodology cites
- FrontierCode 2.0, Score, all tasks (132), Gemini 4 Argon: Cognition’s leaderboard, 18 Nov 2026 · Devin CLI · high effort
- FrontierCode 2.0, Score, all tasks (132), Gemini 4 Neon: Run by Cognition · high thinking · set and measure of the official public leaderboard the evaluation methodology cites
- FrontierCode 2.0, Pass rate, all tasks (132), Gemini 4 Argon: Cognition’s leaderboard, 18 Nov 2026 · Devin CLI · high effort
- FrontierCode 2.0, Pass rate, all tasks (132), Gemini 4 Neon: Cognition’s leaderboard, 18 Nov 2026 · Antigravity CLI · high effort
- Chartography, No tools, Gemini 4 Argon: Run by Surge AI · Surge AI's public leaderboard
- Chartography, No tools, Gemini 4 Neon: highest thinking
- 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
- SEC-bench Pro 260505, Gemini 4 Neon: Antigravity harness · pass@1, mean of 3 attempts · 183-task JavaScript engine split (May 2026) · LLM judge for crashes in both builds · safety filters off
- 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
- Agents' Last Exam v1.1, Score, all tasks (122), Gemini 4 Neon: Antigravity-CLI version 1.4.8 harness · highest thinking · 5-hour window · safety filters on
- GraphWalks, BFS, 256K + 1M problems, Gemini 4 Neon: highest thinking · 200 problems between 256K and 1M tokens
- ExploitGym, Mitigations off, score, Gemini 4 Argon: Antigravity harness · single attempt per task · no internet access · 10h time cap per task, per the Gemini 4 Carbon post’s chart
- ExploitGym, Mitigations off, score, Gemini 4 Neon: Antigravity harness · single attempt per task · no internet access · 10h time cap per task · safety filters off · mitigations off (the default setting), per the model evaluation
- HLE-Diamond, No tools, Gemini 4 Neon: Run by Artificial Analysis · GPT-5.6 Luna (medium) judge with the official HLE judge prompt, per Artificial Analysis’s methodology
- SWE-bench Pro V2, Full set (642 tasks), Gemini 4 Argon: Scale AI’s leaderboard, 18 Nov 2026 · mini-swe-agent · high effort
- SWE-bench Pro V2, HARD-51 (51 tasks), Gemini 4 Argon: Scale AI’s leaderboard, 18 Nov 2026 · mini-swe-agent · high effort
- Terminal-Bench 4.1, Gemini 4 Argon: Stanford University and Laude Institute’s leaderboard, 18 Nov 2026 · Antigravity CLI · high 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
- OSWorld 2.0 (v2026.08.08), Offline set, partial score, Gemini 4 Argon: Gemini CUA harness · max of 3 runs, one attempt per run
- FrontierSWE v2, Gemini 4 Argon: Run by Proximal · Proximal's public leaderboard
- Agents' Last Exam v1, Pass rate, set not specified, Gemini 4 Argon: ALE-Claw harness · 5-hour window · safety filters on
- GraphWalks, BFS, up to 128K, Gemini 4 Argon: 650 problems up to 128K tokens, per the model evaluation document