Gemini 4 Argon
- Family
- Gemini 4
- Released
- 2026-09-30
- Context
- 1M
- Max output
- 1M
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryRestricted
- Weights
- Not released
- Code
- Unknown
- Training
- Pretrained
Cheapest of 4 routes · Google AI Studio · cache read $0.100
Cheapest of 4 routes · Google AI Studio · cache read $0.100
About
Gemini 4 Argon is a Google DeepMind reasoning model, announced on September 30, 2026 for trusted cyber defenders and testers in Google's Fairwind Program and made generally available on October 13, 2026 through the Gemini API, Gemini Enterprise Agent Platform, Google Antigravity and the Gemini app. Google built it for long-horizon software engineering, legal and finance work, cybersecurity defense and science. It takes text, image, video, audio and PDF input and returns text. Input and output share a 1,048,576-token limit; one synchronous request returns up to 65,536 output tokens, and long decodes extend output up to 1,048,576 tokens.
Providers(4)
Compare all 4Compare API pricing across 4 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Cache | Route |
|---|---|---|---|---|---|
| Google AI Studio | $2.00 | $10.00 | $1.00 / $5.00 | read $0.100 | Serverless |
| GCP Vertex AI | $2.00 | $10.00 | $1.00 / $5.00 | read $0.100 | ServerlessProvisioned |
| OpenRouter | $2.00 | $10.00 | $1.00 / $5.00 | read $0.100 | Serverless |
| Vercel AI Gateway | $2.00 | $10.00 | - | read $0.100 | Serverless |
Available via routers & gateways(13)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 500+ models from 80+ providers via a single OpenAI-compatible API, with an optional Auto Router that selects a model per prompt from market spend data.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, caching, and guardrails; MIT-licensed open-source core is self-hostable. Now part of Palo Alto Networks as Prisma AIRS AI Gateway.
AIRouter
RouterCommercial LLM router (branded "AI Router" on its site) that picks the best model per request via a Decision API or an OpenAI-compatible Chat Completions endpoint, with a private selection mode that routes on anonymized patterns; sold as BYOK subscription plans priced by routed tokens.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache-2.0 open-source platform with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
Capabilities
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(11)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 77.9 | DeepSWE v1.1Observed 2026-10-17 | Configuration: Gemini 4 Argon (highest thinking) Harness: mini-swe-agent Evaluator: Google DeepMind Confidence: self-reported Notes: Blog benchmark table (gemini-4-argon_table_blog.gif); evals methodology page https://deepmind.google/models/evals-methodology/gemini-4-argon: self-computed with mini-swe-agent harness, highest thinking level. Retrieved 2026-10-17. | ||
| 39.5 | Agents' Last Exam (binary pass rate)Observed 2026-10-17 | Configuration: Gemini 4 Argon Harness: ALE-Claw (default harness) Evaluator: Google DeepMind Confidence: self-reported Notes: Blog table + methodology page: binary pass rate, ALE-Claw default harness, 5-hour window, safety filters on. Retrieved 2026-10-17. | ||
| 69.2 | OSWorld 2.0 offline subset (partial score)Observed 2026-10-17 | Configuration: Gemini 4 Argon; max of 3 runs Harness: Gemini CUA harness; official OSWorld 2.0 evaluator Evaluator: Google DeepMind Confidence: self-reported Notes: Blog table + methodology page: OSWorld 2.0 offline subset, partial score, max over 3 runs, Gemini CUA harness, official evaluator, 1080p, 500 steps, 08.08 patch. Comparability caveat: max-of-3 and offline subset differ from other OSWorld 2.0 rows. Retrieved 2026-10-17. | ||
| 51.3 | AutomationBench private setObserved 2026-10-17 | Configuration: Gemini 4 Argon; private split Harness: Zapier official AutomationBench evaluation Evaluator: Zapier Confidence: confirmed Notes: Blog table + methodology page: private set figure taken from Zapier's official AutomationBench leaderboard (Zapier-run). Note: most other catalog automation-bench rows are the public split; not directly comparable. Retrieved 2026-10-17. | ||
| 96.4 | diamondObserved 2026-10-17 | Configuration: gemini-4-argon (High) Harness: Epoch AI Inspect harness (GPQA Diamond, 198 Q) Evaluator: Epoch AI Confidence: confirmed Notes: Epoch AI-run evaluation (evaluator of record), from Epoch AI Benchmarking Hub data download https://epoch.ai/data/benchmark_data.zip (file gpqa_diamond.csv, row 'gemini-4-argon_high', run started 2026-10-13). Epoch data is CC BY 4.0: credit 'Epoch AI, Capabilities Benchmarking Hub'. Retrieved 2026-10-17. | ||
| 78.0 | FrontierMath Tier 4 v2 (private)Observed 2026-10-17 | Configuration: gemini-4-argon (High) Harness: Epoch AI FrontierMath Tier 4 v2 private set Evaluator: Epoch AI Confidence: confirmed Notes: Epoch AI-run evaluation (evaluator of record), from Epoch AI Benchmarking Hub data download https://epoch.ai/data/benchmark_data.zip (file frontiermath_tier_4.csv, row 'gemini-4-argon_high', run started 2026-10-13). Epoch data is CC BY 4.0: credit 'Epoch AI, Capabilities Benchmarking Hub'. Retrieved 2026-10-17. | ||
| 91.3 | ARC-AGI-2 semi-privateObserved 2026-10-17 | Configuration: gemini-4-argon (High) Harness: ARC Prize semi-private evaluation Evaluator: ARC Prize Foundation Confidence: confirmed Cost/task: $0.33 Notes: ARC Prize official leaderboard data (ARC-AGI-2 semi-private), verified in https://arcprize.org/media/data/leaderboard/v2.json (generatedAt 2026-10-15T13:43:29Z) for modelDisplayName 'Gemini 4 Argon (High)'; cost $0.325/task. Retrieved 2026-10-17. | ||
| 65.4 | Finance Agent v2 (Vals benchmark_id finance_agent_v2, version 2)Observed 2026-10-17 | Configuration: Vals AI default provider Google; temperature 1, max output 262,144, reasoning effort high Harness: Vals AI Finance Agent harness (Valkyrie) Evaluator: Vals AI Confidence: third-party Cost/task: $4.38 Notes: Vals AI leaderboard (https://www.vals.ai/benchmarks/fabv2), page 'Updated 10/16/2026', retrieved 2026-10-17. Vals model page https://www.vals.ai/models/google_gemini-4-argon shows the hyperparameters. Accuracy; ranked #1 on the page. The lab's restatement (https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/) reads 65.4; it matches after rounding and is not the source of this row. | ||
| 19.6 | Harvey's Legal Agent Benchmark v1 (Vals benchmark_id legal_agent_benchmark)Observed 2026-10-17 | Configuration: Vals AI default provider Google; temperature 1, max output 262,144, reasoning effort high Harness: Harvey generation and grading protocol, run by Vals on Valkyrie, internet disabled Evaluator: Vals AI Confidence: third-party Cost/task: $10.55 Notes: Vals AI leaderboard (https://www.vals.ai/benchmarks/hlab), page 'Updated 10/16/2026', retrieved 2026-10-17. Vals model page https://www.vals.ai/models/google_gemini-4-argon shows the hyperparameters. Metric is the task all-pass rate: a task passes only if 100% of its criteria pass, averaged over two LLM judges (GPT 5.5 medium reasoning, Claude Sonnet 4.6). Vals model page: ±3.31. The lab's restatement (https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/) reads 19.6; it matches after rounding and is not the source of this row. | ||
| 1517.0 | text_style_control overall 2026-10-22 (style control, default view)Observed 2026-10-26 | Configuration: Gemini 4 Argon (High) Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena text style control leaderboard, overall category, published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'Gemini 4 Argon (High)': rank 1, Arena Score 1517.2 (95% CI 1510.6-1523.8), 10083 votes. Retrieved 2026-10-26. | Source Source: LMArena (lmarena.ai), CC BY 4.0 | |
| 1523.0 | text creative_writing 2026-10-22Observed 2026-10-22 | Configuration: Gemini 4 Argon (High) Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 4 Argon (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 2 of 416, rating 1523.1 (95% CI 1509.6-1536.5), 2335 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27. | Source Source: LMArena (lmarena.ai), CC BY 4.0 |
Migration checks
No linked migration route is available for this model yet.