87Leader
Frontier model index · July 2026
Frontier AI Models
Kimi K3 is #7 overall and remains a frontier candidate, not a verified frontier model. The frontier is the current top 10 in each ranking view. Exact-source coverage decides whether a position is verified or stays provisional.
- Frontier size
- 10 models
- Verified frontier
- 3 models
- Candidates
- 7 models
- Leader to cutoff
- 13 pts
Live index
Which models are on the frontier now?
The table changes with the selected capability. Rank comes from the provisional lane; the status badge shows whether exact-source evidence also supports the position.
Cutoff: 74
| Rank | Model | Status | Score | Gap | Output / 1M | Evidence |
|---|---|---|---|---|---|---|
| 01 | Claude Mythos 5Anthropic · Proprietary | Frontier candidate | 87 | Leader | $50 | 15 rows |
| 02 | Claude Opus 4.8Anthropic · Proprietary | Verified frontier | 82 | -5 | $25 | 28 rows |
| 03 | GPT-5.6 SolOpenAI · Proprietary | Frontier candidate | 80 | -7 | $30 | 21 rows |
| 04 | Claude Fable 5Anthropic · Proprietary | Frontier candidate | 80 | -7 | $50 | 10 rows |
| 05 | Claude Sonnet 5Anthropic · Proprietary | Frontier candidate | 79 | -8 | $10 | 15 rows |
| 06 | Qwen3.7 MaxAlibaba · Proprietary | Verified frontier | 78 | -9 | Not listed | 33 rows |
| 07 | Kimi K3Moonshot AI · Pending | Frontier candidate | 78 | -9 | $15 | 29 rows |
| 08 | GPT-5.6 TerraOpenAI · Proprietary | Frontier candidate | 77 | -10 | $15 | 20 rows |
| 09 | Muse Spark 1.1Meta · Proprietary | Frontier candidate | 75 | -12 | Not listed | 19 rows |
| 10 | GPT-5.5OpenAI · Proprietary | Verified frontier | 74 | -13 | $30 | 29 rows |
#ModelScore
82-5 pts
GPT-5.6 SolOpenAI · 21 exact rowsCandidate
80-7 pts
80-7 pts
79-8 pts
78-9 pts
Kimi K3Moonshot AI · 29 exact rowsCandidate
78-9 pts
GPT-5.6 TerraOpenAI · 20 exact rowsCandidate
77-10 pts
Muse Spark 1.1Meta · 19 exact rowsCandidate
75-12 pts
GPT-5.5OpenAI · 29 exact rowsVerified
74-13 pts
Method
Where we draw the line
Frontier membership is deliberately narrow: the ten highest provisional scores in the selected view. Verification is a second gate. A model needs at least 8 exact-source benchmark rows, plus eligible coverage across two or more categories, before its position moves into the verified lane.
Missing rows are not filled in. External consensus can support a provisional rank, but it cannot grant verified status.
- 01
Rank
Order eligible models by the selected score.
- 02
Cut
Keep the first ten rows.
- 03
Verify
Apply exact-source coverage gates.
Cost check
The price of frontier performance
The top score and the cheapest acceptable score are often different buying decisions. This view keeps the evidence status attached to both.
Upper-left is better
Scores use the selected frontier view. Prices are official output-token rates in USD per million tokens.
Lowest priced frontier API
Claude Sonnet 5
$10 / 1M out
Baseline ledger
What changed this month
Kimi K3
CandidateReleased this month and currently #7 as a frontier candidate.
GPT-5.6 Sol
CandidateReleased this month and currently #3 as a frontier candidate.
GPT-5.6 Terra
CandidateReleased this month and currently #8 as a frontier candidate.
Muse Spark 1.1
CandidateReleased this month and currently #9 as a frontier candidate.