Side-by-side comparison · models
Gemini 4 Argon vs Gemma 4 26B A4B (free)
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
Gemini 4 Argon
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.
Models
Gemma 4 26B A4B (free)
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Checked facts
Line by line
| Measure | Gemini 4 Argon | Gemma 4 26B A4B (free) |
|---|---|---|
| Input price | $2.00 per million tokens | Not checked yet |
| Output price | $10.00 per million tokens | Not checked yet |
| Price on google-ai-studio | $0.050 per million cached input tokens | Not checked yet |
| Price on google-ai-studio | $1.00 per million input tokens | Not checked yet |
| Price on google-ai-studio | $5.00 per million output tokens | Not checked yet |
| Price on google-vertex | $0.100 per million cached input tokens | Not checked yet |
| Price on google-vertex | $2.00 per million input tokens | $0.150 per million input tokens |
| Price on google-vertex | $10.00 per million output tokens | $0.600 per million output tokens |
| Price on akashml | Not checked yet | $0.046 per million cached input tokens |
| Price on akashml | Not checked yet | $0.070 per million input tokens |
| Price on akashml | Not checked yet | $0.240 per million output tokens |
| Price on cloudflare | Not checked yet | $0.050 per million cached input tokens |
| Price on cloudflare | Not checked yet | $0.100 per million input tokens |
| Price on cloudflare | Not checked yet | $0.300 per million output tokens |
| Price on coreweave | Not checked yet | $0.050 per million cached input tokens |
| Price on coreweave | Not checked yet | $0.100 per million input tokens |
| Price on coreweave | Not checked yet | $0.300 per million output tokens |
| Price on darkbloom | Not checked yet | $0.010 per million cached input tokens |
| Price on darkbloom | Not checked yet | $0.040 per million input tokens |
| Price on darkbloom | Not checked yet | $0.150 per million output tokens |
| Price on deepinfra | Not checked yet | $0.070 per million input tokens |
| Price on deepinfra | Not checked yet | $0.340 per million output tokens |
| Price on dekallm | Not checked yet | $0.040 per million cached input tokens |
| Price on dekallm | Not checked yet | $0.060 per million input tokens |
| Price on dekallm | Not checked yet | $0.330 per million output tokens |
| Price on io-net | Not checked yet | $0.037 per million cached input tokens |
| Price on io-net | Not checked yet | $0.081 per million input tokens |
| Price on io-net | Not checked yet | $0.279 per million output tokens |
| Price on makora | Not checked yet | $0.046 per million cached input tokens |
| Price on makora | Not checked yet | $0.080 per million input tokens |
| Price on makora | Not checked yet | $0.100 per million output tokens |
| Price on nextbit | Not checked yet | $0.050 per million cached input tokens |
| Price on nextbit | Not checked yet | $0.090 per million input tokens |
| Price on nextbit | Not checked yet | $0.300 per million output tokens |
| Price on novita | Not checked yet | $0.130 per million input tokens |
| Price on novita | Not checked yet | $0.400 per million output tokens |
| Price on parasail | Not checked yet | $0.050 per million cached input tokens |
| Price on parasail | Not checked yet | $0.130 per million input tokens |
| Price on parasail | Not checked yet | $0.400 per million output tokens |
| Price on prime-intellect | Not checked yet | $0.0060 per million cached input tokens |
| Price on prime-intellect | Not checked yet | $0.012 per million input tokens |
| Price on prime-intellect | Not checked yet | $0.037 per million output tokens |
| Price on siliconflow | Not checked yet | $0.050 per million cached input tokens |
| Price on siliconflow | Not checked yet | $0.140 per million input tokens |
| Price on siliconflow | Not checked yet | $0.400 per million output tokens |
| Price on venice | Not checked yet | $0.050 per million cached input tokens |
| Price on venice | Not checked yet | $0.130 per million input tokens |
| Price on venice | Not checked yet | $0.400 per million output tokens |
| Latest version | google/gemini-4-argon-20261013 | google/gemma-4-26b-a4b-it-20260403 |
| Time to first token (ms) | 51,560 | 940 |
| Time to first token (ms) on google-ai-studio | 9,010 | Not checked yet |
| Time to first token (ms) on google-vertex | 5,894 | 674 |
| Output speed (tokens a second) | 87 | 104.7 |
| Output speed (tokens a second) on google-ai-studio | 48 | Not checked yet |
| Output speed (tokens a second) on google-vertex | 26 | 43 |
| Time to first token (ms) on akashml | Not checked yet | 951 |
| Time to first token (ms) on cloudflare | Not checked yet | 725 |
| Time to first token (ms) on coreweave | Not checked yet | 381 |
| Time to first token (ms) on darkbloom | Not checked yet | 739 |
| Time to first token (ms) on deepinfra | Not checked yet | 381 |
| Time to first token (ms) on dekallm | Not checked yet | 810 |
| Time to first token (ms) on io-net | Not checked yet | 755 |
| Time to first token (ms) on makora | Not checked yet | 466 |
| Time to first token (ms) on nextbit | Not checked yet | 349 |
| Time to first token (ms) on novita | Not checked yet | 708 |
| Time to first token (ms) on parasail | Not checked yet | 423 |
| Time to first token (ms) on prime-intellect | Not checked yet | 931 |
| Time to first token (ms) on siliconflow | Not checked yet | 1,253 |
| Time to first token (ms) on venice | Not checked yet | 689 |
| Output speed (tokens a second) on akashml | Not checked yet | 54 |
| Output speed (tokens a second) on cloudflare | Not checked yet | 47 |
| Output speed (tokens a second) on coreweave | Not checked yet | 41 |
| Output speed (tokens a second) on darkbloom | Not checked yet | 47 |
| Output speed (tokens a second) on deepinfra | Not checked yet | 49 |
| Output speed (tokens a second) on dekallm | Not checked yet | 53 |
| Output speed (tokens a second) on io-net | Not checked yet | 55 |
| Output speed (tokens a second) on makora | Not checked yet | 81 |
| Output speed (tokens a second) on nextbit | Not checked yet | 75 |
| Output speed (tokens a second) on novita | Not checked yet | 104 |
| Output speed (tokens a second) on parasail | Not checked yet | 108 |
| Output speed (tokens a second) on prime-intellect | Not checked yet | 30 |
| Output speed (tokens a second) on siliconflow | Not checked yet | 62 |
| Output speed (tokens a second) on venice | Not checked yet | 55 |
| Tokens served on OpenRouter in a day | 139.9B (for 10 Nov 2026) | Not checked yet |
| Tool calls on OpenRouter in a day | 742.5K (for 10 Nov 2026) | Not checked yet |
| Artificial Analysis Intelligence Index | 50.4 | Not checked yet |
| LMArena text rating (Elo) | 1,530 | Not checked yet |
| LMArena web development rating (Elo) | 1,682 | Not checked yet |
| Design Arena rating (Elo) | 1,374 | Not checked yet |
| Gpqa diamond | 96.4% (for 30 Sept 2026) | 73.2% (for 2 Apr 2026) |
| Frontiermath tiers 1 3 v2 private | 86% (for 30 Sept 2026) | Not checked yet |
| Simpleqa verified | 76% (for 30 Sept 2026) | Not checked yet |
| Arc agi 2 | 91.3% (for 30 Sept 2026) | Not checked yet |
| Apex agents | 82.4% (for 30 Sept 2026) | Not checked yet |
| Arc agi | 98.5% (for 30 Sept 2026) | Not checked yet |
| Chess puzzles | 59% (for 30 Sept 2026) | Not checked yet |
| Dtbench | 97.6% (for 30 Sept 2026) | 74.9% (for 2 Apr 2026) |
| Ebr bench | 64.8% (for 30 Sept 2026) | Not checked yet |
| Frontiercode | 47.6% (for 30 Sept 2026) | Not checked yet |
| Frontiermath tier 4 v2 private | 78% (for 30 Sept 2026) | Not checked yet |
| Frontierswe | 55% (for 30 Sept 2026) | Not checked yet |
| Furniture assembly | 72.5% (for 30 Sept 2026) | Not checked yet |
| Lmca | 63.7% (for 30 Sept 2026) | 29.7% (for 2 Apr 2026) |
| Mirrorcode | 58.9% (for 30 Sept 2026) | Not checked yet |
| Mystery game puzzles | 64% (for 30 Sept 2026) | Not checked yet |
| Proofbench | 99% (for 30 Sept 2026) | Not checked yet |
| Weirdml v3 | 41.4% (for 30 Sept 2026) | Not checked yet |
| Otis mock aime 2024 2025 | 100% (saturated benchmark: the top models all score near the ceiling) (for 30 Sept 2026) | 82.2% (saturated benchmark: the top models all score near the ceiling) (for 2 Apr 2026) |
| Weirdml | Not checked yet | 35.2% (for 2 Apr 2026) |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.