Compare / head-to-head
Gemini 4 Argonvs
Inkling-Small
Gemini 4 Argon leads 5 of 5 shared benchmarks. Inkling-Small is 8x cheaper per token.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
5 – 0
Gemini 4 Argon leads
Cheaper per token
Inkling-Small
8x cheaper, input + output
Larger context
—
unknown
Providers
2 providers
Google · Thinking Machines Lab
Gemini 4 Argon
Google · released 2026-09-30
textvisionvideo
Inkling-Small
Thinking Machines Lab · released 2026-07-30
textvisionaudio
Quality
Benchmark matrix
5 shared · 7 only Gemini 4 Argon · 23 only Inkling-Small| Benchmark | Gemini 4 Argon | Inkling-Small | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| LMArena Elo | 1525.2 ↗ | 1405.2 ↗ | +120 | Gemini 4 Argon |
| LMArena Agent (LMArena) | 0.0757 ↗ | -0.1033 ↗ | +0.2 | Gemini 4 Argon |
| LMArena WebDev (LMArena) | 1679.5 ↗ | 1408.2 ↗ | +271.3 | Gemini 4 Argon |
| SAGE (Vals AI) | 53.6% ↗ | 32.7% ↗ | +20.9 pt | Gemini 4 Argon |
| Terminal-Bench 4.0 (Vals AI) | 57.6% ↗ | 0% ↗ | +57.6 pt | Gemini 4 Argon |
| Only Gemini 4 Argon reports · 7 | ||||
| APEX-Agents (Mercor) | 82.2% ↗ | not reported | — | — |
| AutomationBench | 51.3% ↗ | not reported | — | — |
| CWE-bench v1 | 68% ↗ | not reported | — | — |
| DeepSWE v1.1 | 77.9% ↗ | not reported | — | — |
| FrontierSWE V2 (Proximal Labs) | 55% ↗ | not reported | — | — |
| LVBench | 91.7% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 13718.16 ↗ | not reported | — | — |
| Only Inkling-Small reports · 23 | ||||
| SWE-bench Verified | not reported | 80.2% ↗ | — | — |
| GPQA Diamond | not reported | 88.5% ↗epoch run | — | — |
| AIME 2026 | not reported | 95.5% ↗ | — | — |
| ARC-AGI-1 | not reported | 84% ↗ | — | — |
| ARC-AGI-2 | not reported | 40.1% ↗ | — | — |
| BrowseComp (with context management) | not reported | 77.4% ↗ | — | — |
| CharXiv RQ | not reported | 77.4% ↗ | — | — |
| CharXiv RQ (with python) | not reported | 81.3% ↗ | — | — |
| Chess Puzzles (Epoch AI run) | not reported | 18% ↗epoch run | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 17.1% ↗epoch run | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 46.3% ↗epoch run | — | — |
| HMMT Feb 2026 | not reported | 90.2% ↗ | — | — |
| IFBench | not reported | 82.2% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1206.3 ↗ | — | — |
| MCP Atlas (all) | not reported | 79.2% ↗ | — | — |
| MMAU | not reported | 77% ↗ | — | — |
| Mystery Game Puzzles (Epoch AI run) | not reported | 6% ↗epoch run | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 90% ↗epoch run | — | — |
| SimpleQA Verified | not reported | 20.6% ↗ | — | — |
| SWE-bench Pro (public) | not reported | 55.9% ↗ | — | — |
| Terminal-Bench 2.1 (best harness) | not reported | 64.7% ↗ | — | — |
| Toolathlon Verified | not reported | 54.4% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 54.4% ↗ | — | — |
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-Small 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-Small | Edge |
|---|---|---|---|
| Context window | — | 1M tokens | — |
| Max output | 1M tokens | — | — |
| Input price / 1M | $2 ↗ | $0.3 ↗ | Inkling-Small |
| Output price / 1M | $10 ↗ | $1.2 ↗ | Inkling-Small |
| Cached input / 1M | $0.1 ↗ | $0.06 ↗ | Inkling-Small |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $12 | $1.5 | Inkling-Small |
| Modalities | text · vision · video | text · vision · audio | Tie |
| Released | 2026-09-30 | 2026-07-30 | — |
| Cited benchmark scores | 12 | 29 | — |
Reliability
Provider status
Live from /statusMore matchups
Gemini 4 Argon vs …
Models sharing the most benchmarksMore matchups
Inkling-Small 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-Small on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.