Model frontiers
Models that are not dominated across intelligence and cost or latency.
Snapshot: August 4, 2026
Intelligence versus benchmark execution cost
Artificial Analysis Intelligence Index · Higher is better
- Eligible
- 129
- Candidates
- 591
- Coverage
- 21.8%
| Rank | Model | Creator | Artificial Analysis Intelligence Index | Since prior snapshot |
|---|---|---|---|---|
| 1 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 60.7 | No change |
| 2 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | 60.1 | No change |
| 3 | Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic | 58.9 | Not comparable |
Intelligence versus end-to-end response time
Artificial Analysis Intelligence Index · Higher is better
- Eligible
- 299
- Candidates
- 591
- Coverage
- 50.6%
| Rank | Model | Creator | Artificial Analysis Intelligence Index | Since prior snapshot |
|---|---|---|---|---|
| 1 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 60.7 | No change |
| 2 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | 60.1 | No change |
| 3 | Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic | 58.9 | No change |
Intelligence versus local 3:1 token price
Artificial Analysis Intelligence Index · Higher is better
- Eligible
- 373
- Candidates
- 591
- Coverage
- 63.1%
| Rank | Model | Creator | Artificial Analysis Intelligence Index | Since prior snapshot |
|---|---|---|---|---|
| 1 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 60.7 | No change |
| 2 | Kimi K3 (max) | Kimi | 57.1 | No change |
| 3 | GPT-5.6 Terra (max) | OpenAI | 55 | No change |
Data source: Artificial Analysis .