Coverage
By lab
| Lab | Events | Model releases | Models | Scores |
|---|
| OpenAIFull | 187 | 52 | 21 | 131 |
|---|
| AnthropicFull | 155 | 27 | 25 | 202 |
|---|
| GoogleFull | 187 | 95 | 21 | 73 |
|---|
| MetaModel releases | 11 | 11 | 9 | 41 |
|---|
| DeepSeekModel releases | 13 | 13 | 14 | 62 |
|---|
| MistralModel releases | 18 | 18 | 6 | 22 |
|---|
| AlibabaModel releases | 27 | 27 | 17 | 92 |
|---|
| Moonshot AIModel releases | 5 | 5 | 5 | 29 |
|---|
| MiniMaxModel releases | 7 | 7 | 7 | 40 |
|---|
| Z.aiModel releases | 9 | 9 | 8 | 77 |
|---|
| NVIDIAModel releases | 10 | 10 | 9 | 93 |
|---|
| xAIMilestones | 1 | 1 | 0 | 0 |
|---|
| SnowflakeMilestones | 1 | 1 | 0 | 0 |
|---|
| SberMilestones | 1 | 1 | 0 | 0 |
|---|
| Thinking MachinesMilestones | 1 | 1 | 1 | 4 |
|---|
| PoolsideMilestones | 1 | 1 | 1 | 2 |
|---|
By importance
| Importance | Events |
|---|
| Milestone | 33 |
|---|
| Major | 205 |
|---|
| Minor | 396 |
|---|
Benchmark scores by check
| Check | Scores |
|---|
| Entered twice, independently | 868 |
|---|
| Corroborated by a second lab document | 493 |
|---|
| Checked by a person | 692 |
|---|
Benchmarks by status
| Status | Benchmarks | Scores |
|---|
| Active | 12 | 589 |
|---|
| Superseded | 7 | 132 |
|---|
| Retired | 6 | 147 |
|---|