Model frontiers
Models that are not dominated across intelligence and cost or latency.
Last validated snapshot: October 27, 2026
Analysis
Intelligence versus benchmark execution cost
Artificial Analysis Intelligence Index · Higher is better
- Eligible
- 201
- Candidates
- 715
- Coverage
- 28.1%
| Rank | Model | Creator | Artificial Analysis Intelligence Index | Since prior snapshot |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 (Max, Default Fallback) | Anthropic | 57.6 | Not comparable |
| 2 | Claude Opus 5.5 (Xhigh, Default Fallback) | Anthropic | 56 | Not comparable |
| 3 | Kimi K3.1 Pro | Kimi | 55.1 | Not comparable |
Intelligence versus end-to-end response time
Artificial Analysis Intelligence Index · Higher is better
- Eligible
- 375
- Candidates
- 715
- Coverage
- 52.4%
| Rank | Model | Creator | Artificial Analysis Intelligence Index | Since prior snapshot |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 (Max, Default Fallback) | Anthropic | 57.6 | Not comparable |
| 2 | Claude Opus 5.5 (Xhigh, Default Fallback) | Anthropic | 56 | Not comparable |
| 3 | Kimi K3.1 Pro | Kimi | 55.1 | Not comparable |
Intelligence versus local 3:1 token price
Artificial Analysis Intelligence Index · Higher is better
- Eligible
- 429
- Candidates
- 715
- Coverage
- 60.0%
| Rank | Model | Creator | Artificial Analysis Intelligence Index | Since prior snapshot |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 (Max, Default Fallback) | Anthropic | 57.6 | Not comparable |
| 2 | Claude Sonnet 5.5 (Max, Default Fallback) | Anthropic | 56 | Not comparable |
| 3 tie | Muse Spark 1.3 (Max) | Meta | 48.1 | No change |
| 3 tie | GPT-6.1 Terra (Max) | OpenAI | 48.1 | Not comparable |
Data source: Artificial Analysis .