Compare / head-to-head
Gemini 4 Argonvs
Inkling
Gemini 4 Argon leads 7 of 7 shared benchmarks. Inkling is 2.4x cheaper per token.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
7 – 0
Gemini 4 Argon leads
Cheaper per token
Inkling
2.4x cheaper, input + output
Larger context
—
unknown
Providers
2 providers
Google · Thinking Machines Lab
Gemini 4 Argon
Google · released 2026-09-30
textvisionvideo
Quality
Benchmark matrix
7 shared · 5 only Gemini 4 Argon · 31 only Inkling| Benchmark | Gemini 4 Argon | Inkling | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| LMArena Elo | 1525.2 ↗ | 1441.4 ↗ | +83.8 | Gemini 4 Argon |
| APEX-Agents (Mercor) | 82.2% ↗ | 33.8% ↗ | +48.4 pt | Gemini 4 Argon |
| FrontierSWE V2 (Proximal Labs) | 55% ↗ | 4.1% ↗ | +50.9 pt | Gemini 4 Argon |
| LMArena Agent (LMArena) | 0.0757 ↗ | -0.1086 ↗ | +0.2 | Gemini 4 Argon |
| LMArena WebDev (LMArena) | 1679.5 ↗ | 1412.6 ↗ | +266.9 | Gemini 4 Argon |
| SAGE (Vals AI) | 53.6% ↗ | 36.6% ↗ | +17 pt | Gemini 4 Argon |
| Terminal-Bench 4.0 (Vals AI) | 57.6% ↗ | 0.5% ↗ | +57.1 pt | Gemini 4 Argon |
| Only Gemini 4 Argon reports · 5 | ||||
| AutomationBench | 51.3% ↗ | not reported | — | — |
| CWE-bench v1 | 68% ↗ | not reported | — | — |
| DeepSWE v1.1 | 77.9% ↗ | not reported | — | — |
| LVBench | 91.7% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 13718.16 ↗ | not reported | — | — |
| Only Inkling reports · 31 | ||||
| SWE-bench Verified | not reported | 77.6% ↗ | — | — |
| GPQA Diamond | not reported | 88.3% ↗epoch run | — | — |
| AIME 2026 | not reported | 97.1% ↗ | — | — |
| Audio MC | not reported | 56.6% ↗ | — | — |
| BrowseComp (w/ ctx management) | not reported | 77.1% ↗ | — | — |
| CharXiv RQ | not reported | 78.1% ↗ | — | — |
| CharXiv RQ (with python) | not reported | 82% ↗ | — | — |
| Chess Puzzles (Epoch AI run) | not reported | 21% ↗epoch run | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 4.9% ↗epoch run | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 33.3% ↗epoch run | — | — |
| Global-MMLU-Lite | not reported | 88.7% ↗ | — | — |
| IFBench | not reported | 79.8% ↗ | — | — |
| LiveBench Agentic Coding (LiveBench) | not reported | 49.4% ↗ | — | — |
| LiveBench Coding (LiveBench) | not reported | 71% ↗ | — | — |
| LiveBench Data Analysis (LiveBench) | not reported | 72.8% ↗ | — | — |
| LiveBench Instruction Following (LiveBench) | not reported | 70.1% ↗ | — | — |
| LiveBench Language (LiveBench) | not reported | 73.5% ↗ | — | — |
| LiveBench Mathematics (LiveBench) | not reported | 88.4% ↗ | — | — |
| LiveBench Reasoning (LiveBench) | not reported | 78.3% ↗ | — | — |
| MCP Atlas | not reported | 76% ↗ | — | — |
| MMAU | not reported | 77.2% ↗ | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 88.9% ↗epoch run | — | — |
| SimpleBench (SimpleBench) | not reported | 50% ↗ | — | — |
| SimpleQA Verified | not reported | 43.9% ↗ | — | — |
| SWE-bench Pro (public) | not reported | 54.3% ↗ | — | — |
| tau2-bench Banking Knowledge (Sierra) | not reported | 25% ↗ | — | — |
| Terminal-Bench 2.1 (best harness) | not reported | 63.8% ↗ | — | — |
| Toolathlon Verified | not reported | 45.5% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 45.5% ↗ | — | — |
| VoiceBench | not reported | 91.4% ↗ | — | — |
| WeirdML (Håvard Tveit Ihle) | not reported | 32.3% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Gemini 4 Argon minus Inkling in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Gemini 4 Argon | Inkling | Edge |
|---|---|---|---|
| Context window | — | 1M tokens | — |
| Max output | 1M tokens | — | — |
| Input price / 1M | $2 ↗ | $1 ↗ | Inkling |
| Output price / 1M | $10 ↗ | $4.05 ↗ | Inkling |
| Cached input / 1M | $0.1 ↗ | $0.17 ↗ | Gemini 4 Argon |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $12 | $5.05 | Inkling |
| Modalities | text · vision · video | text · vision · audio | Tie |
| Released | 2026-09-30 | 2026-07-15 | — |
| Cited benchmark scores | 12 | 39 | — |
Reliability
Provider status
Live from /statusMore matchups
Gemini 4 Argon vs …
Models sharing the most benchmarksMore matchups
Inkling vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Gemini 4 Argon and Inkling on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.