Gemini 4 Argon
Lineage
- Company
- Google
- Family
- Gemini 4 Argon
- Assistants that offer it
- Geminipaid plan, Google AI Pro, AI Ultra (official page ↗)
Perplexitypaid plan, Max (official page ↗) - API price
- 2 $ per million tokens read, 10 $ written (aistudio.google.com/docs/pricing, read on 5 November 2026)
Links read on 10/11/2026 on company pages, the press as a fallback; a link given for a family applies only to its latest version.
Rank in each benchmark
- General intelligenceEpoch AI, ECI index166.5163.9 to 169.57th out of 71
- User preferenceLMArena, Elo score15222nd out of 68
- Agent tasksEpoch AI, APEX-Agents82.4 %74.0 to 90.82nd out of 52
- Coding tasksEpoch AI, CursorBench52.9 %3rd out of 18
- Code repairEpoch AI, DeepSWEnot measured
Each segment of the bar is worth a tenth of the ranking; the 1st groups the best ranked. Rank among models released in 2026 and measured by the benchmark. Sources: Epoch AI, "Capabilities & benchmarking" (CC BY 4.0); LMArena, text with style control (CC BY 4.0); data as of 10 November 2026.
Success and electricity use of Gemini 4 Argon by effort setting
CursorBench benchmark, 4 settings; electricity use of a task in Wh, estimate, logarithmic scale; data as of 10 November 2026
Line: from setting to setting, at the middle of the rangeBar: the electricity use of a task, from "all read" to "all written" (estimate)
Sources: Epoch AI, CursorBench; electricity: Projet Celsius estimate, AI Impact Database (IA-0011). Licence CC BY 4.0.
Estimation methodology
The effort setting says how much the model reasons before answering: the higher it is, the more tokens it writes, and the more electricity the task needs. Tokens per task are measured by Epoch AI.
Electricity: Projet Celsius estimate. Tokens of the task × electricity ofwriting 1,000 tokens for the size of the model (AI Impact Database, IA-0011), × the data centre overhead (PUE). The scope covers computing on the servers and cooling; it does not cover chip manufacturing, training, the network or the device. CursorBench counts tokens read and written together: the range runs from "all read" to "all written". DeepSWE counts tokens written: the range starts from writing alone.
Assumed model size: medium class, deduced from the output price (aistudio.google.com/docs/pricing), assumption. If the model were small, the estimate would be 6 times lower; if it were large, 4 times higher. Benchmark: a quick question to an assistant needs about 0.3 Wh.
Gemini 4 Argon among Google's models, general intelligence
Epoch AI ECI index and its 95% interval, by release date; 9 Google models released in 2026 and measured by the ECI index
Dot: the index measured, at the release dateLine: the 95% intervalGemini 4 Argon
Source: Epoch AI, "Capabilities & benchmarking", ECI index. CC BY 4.0 licence.
On a coding task, Gemini 4 Argon needs 25 to 76 Wh at its most demanding setting, as much as about 83 to 250 quick questions to an assistant (about 0.3 Wh each).
Continue in the ranking
The full ranking →CompanyGoogle11models measured, of which 8 with an entryIts assistant, its models, its governance and the electricity of its data centres.The entry →AssistantGemini71out of 100, 2nd out of 10One of the 2 assistants in the ranking that offer Gemini 4 Argon.The entry →RankingAI modelsAgent tasks2ndof 52, agent tasksThe ranking where Gemini 4 Argon is best placed.The ranking →The hub newsletter
This month's ranking, news on the impact of AI and one figure from the AI Impact Database. One newsletter a month at most, free of charge. Past issues
