Best LLM with audio input
- Gemini 4 Argon leads
- 84.0
- models ranked
- 17
- lead over #2
- +15.0
Overall index · read October 22
As of October 22, 2026, Google Gemini 4 Argon leads 17 models that qualify, with 84.0 on the overall index, ahead of Google Gemini 3.8 Flash (69.0) and Xiaomi MiMo-V2.6-Pro (68.4).
| Rank | Model | Overall index | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Gemini 4 Argon Google | 84.0 | 81.0 | $10.00 | |
| 2 | Gemini 3.8 Flash Google | 69.0 | 61.6 | $3.75 | |
| 3 | MiMo-V2.6-Pro Xiaomi | 68.4 | 65.4 | $0.87 | |
| 4 | Gemini 3.6 Flash Google | 68.3 | 62.5 | $3.75 | |
| 5 | Gemini 3.7 Flash Google | 65.7 | 58.0 | $3.75 | |
| 6 | Gemini 3.5 Flash Google | 63.8 | 39.8 | $9.00 | |
| 7 | MiMo-V2.6-Flash Xiaomi | 60.8 | 54.7 | $0.28 | |
| 8 | Gemini 3 Flash Preview Google | 55.0 | 43.7 | $3.00 | |
| 9 | Gemini 3.1 Pro Preview Google | 54.0 | 32.3 | $12.00 | |
| 10 | MiMo-V2.5 Xiaomi | 50.7 | 50.0 | $0.336 | |
| 11 | Gemini 3.5 Flash Lite Google | 49.8 | 49.0 | $2.50 | |
| 12 | T Inkling Thinking Machines | 46.5 | 31.5 | $4.05 | |
| 13 | Muse Spark Open Meta | 44.9 | 47.4 | $4.25 | |
| 14 | T Inkling Small Thinking Machines | 43.6 | 27.3 | $1.20 | |
| 15 | Gemini 2.5 Pro Google | 41.8 | 19.1 | $10.00 | |
| 16 | 36.6 | 22.7 | $1.50 | ||
| 17 | Gemini 2.5 Flash Google | 34.3 | Not benchmarked | $2.50 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Models whose OpenRouter listing takes audio as input, ordered by the LLMBenchmark Index, highest first. The index is our own 0 to 100 composite of our five skill indexes, the Artificial Analysis Intelligence Index and the LMArena text Elo, with a 90% margin.
- OpenRouter, fetched
- LMArena WebDev, fetched
- Artificial Analysis (via OpenRouter), fetched