Model family · 14 versions tracked
Llama: every version compared
Meta: Muse Wonder currently leads the Llama family with an Artificial Analysis Intelligence Index of 43.6. For the best value within the family, Meta: Muse Glimmer 30B (batch) costs $0.52/1M tokens blended.
- Meta: Muse Wonder - 43.6 intelligence · $8.00/1M
- Meta: Muse Spark 1.2 - 39.6 intelligence · $2.00/1M
- Meta: Muse Spark 1.3 - 36.6 intelligence · $2.00/1M
- Meta: Muse Spark 1.1 - 33.7 intelligence · $2.00/1M
- Meta: Muse Spark Open - 24.9 intelligence · $2.00/1M
- Meta: Muse Glimmer 30B (batch) - 6.3 intelligence · $0.52/1M
- Meta: Llama 3.1 8B Instruct - - intelligence · $0.06/1M
- Meta: Llama 3.1 70B Instruct - - intelligence · $0.72/1M
- Meta: Llama 3.2 1B Instruct - - intelligence · $0.07/1M
- Meta: Llama 3.2 3B Instruct - - intelligence · $0.12/1M
- Meta: Llama Guard 4 12B - - intelligence · $0.18/1M
- Meta: Llama 3.3 70B Instruct - - intelligence · $0.64/1M
- Meta: Muse Spark 1.2 Contributor - - intelligence · $0.13/1M
- Meta: Muse Spark 1.3 Contributor - - intelligence · $0.13/1M
| # | Model | Intelligence index | Price/1M blended |
|---|---|---|---|
| 01 | Meta: Muse Wonder | 43.6 | $8.00 |
| 02 | Meta: Muse Spark 1.2 | 39.6 | $2.00 |
| 03 | Meta: Muse Spark 1.3 | 36.6 | $2.00 |
| 04 | Meta: Muse Spark 1.1 | 33.7 | $2.00 |
| 05 | Meta: Muse Spark Open | 24.9 | $2.00 |
| 06 | Meta: Muse Glimmer 30B (batch) | 6.3 | $0.52 |
| 07 | Meta: Llama 3.1 8B Instruct | - | $0.06 |
| 08 | Meta: Llama 3.1 70B Instruct | - | $0.72 |
| 09 | Meta: Llama 3.2 1B Instruct | - | $0.07 |
| 10 | Meta: Llama 3.2 3B Instruct | - | $0.12 |
| 11 | Meta: Llama Guard 4 12B | - | $0.18 |
| 12 | Meta: Llama 3.3 70B Instruct | - | $0.64 |
| 13 | Meta: Muse Spark 1.2 Contributor | - | $0.13 |
| 14 | Meta: Muse Spark 1.3 Contributor | - | $0.13 |
Llama real usage share, over time
Ranked by current quality, not release date - this pipeline's data collection started recently, so "first tracked" timestamps don't reflect true historical release dates yet. The usage-share chart above is real, unaffected by that limitation.
Frequently asked questions
What is the best Llama model?
Meta: Muse Wonder currently leads the Llama family with an Artificial Analysis Intelligence Index of 43.6.
How much real usage does Llama get?
Llama models account for 1.1% of real OpenRouter token volume as of the latest data.
