Gemini 2.5 Pro vs Gemini 4 Argon
| Spec | Gemini 2.5 Pro | Gemini 4 Argon |
|---|---|---|
| Respan Index | 23.1 (#102) | 69.1 (#8) |
| Blended price per 1M | $3.44 | $2 |
| Context window | 1.0M | - |
| Input / output per 1M | $1.25 / $10 | $1 / $5 |
| Max output | 66K | 1M |
| Input | text, vision, audio | text, vision, video |
| Released | 2025-06-17 | 2026-09-30 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Gemini 2.5 Pro | Gemini 4 Argon |
|---|---|---|
| Coding | 3.2 Gemini 2.5 Pro | 55.9 Gemini 4 Argon |
| Agents | 31.0 Gemini 2.5 Pro | 77.1 Gemini 4 Argon |
| Reasoning | 24.5 Gemini 2.5 Pro | 78.1 Gemini 4 Argon |
| Knowledge & language | 14.8* Gemini 2.5 Pro | 76.0 Gemini 4 Argon |
| Human preference | 46.3 Gemini 2.5 Pro | 58.3 Gemini 4 Argon |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
Gemini 4 Argon leads on 9 of the 9 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Gemini 2.5 Pro | Gemini 4 Argon |
|---|---|---|
| LMArena Elo | 1445 | 1520 |
| LMArena WebDev (LMArena) | 1226 | 1679 |
| Chess Puzzles (Epoch AI) | 20% | 59% |
| FrontierMath Tier 4 v2 (Epoch AI) | 0% | 78% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 24.6% | 86% |
| GPQA Diamond | 86.4% | 96.4% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 84.7% | 100% |
| SAGE (Vals AI) | 41.9% | 53.6% |
| Vending-Bench 2 (Andon Labs) | 573.64 | 13718.16 |
FAQ
Is Gemini 2.5 Pro better than Gemini 4 Argon?
Gemini 4 Argon scores 69.1 on the Respan Index (#8), ahead of Gemini 2.5 Pro at 23.1 (#102). Gemini 4 Argon leads on 9 of the 9 benchmarks both report.
Which is cheaper, Gemini 2.5 Pro or Gemini 4 Argon?
Gemini 2.5 Pro lists at $1.25 input and $10 output per 1M tokens; Gemini 4 Argon at $1 and $5. Gemini 4 Argon is 1.7x cheaper per token at list price.