Model releases, capability-per-dollar, training compute & safety posture
The frontier is a four-lab race (Anthropic, OpenAI, Google, Meta) measured four ways: release cadence by quarter, capability-per-dollar (a top model scores ~62 on the AA Intelligence Index at ~$25/M output tokens), training compute rising off a ~3.1e23-FLOP GPT-3 baseline (2020), and a safety-posture matrix.
The pattern: capability keeps climbing while the price of a given capability level keeps falling, the two moving in opposite directions is the whole story.
The Frontier AI Model Race (2026)
- June 2026
- Official body or company filing
- 21
- 8
- 21 actual
Caveat: FLOP figures are third-party estimates (Epoch AI), not disclosed by labs.
This page can answer
Four series on the 2026 frontier-model race: quarterly releases by lab, a capability-vs-cost scatter of leading models, an estimated training-compute (FLOP) trend, and an editorial safety-posture matrix across risk domains.
It cannot answer
- Exact, lab-disclosed training compute (FLOP figures are third-party estimates).
- Real-world safety outcomes (the matrix is a posture summary on an editorial scale).
- Market share or revenue by lab (not in this index).
Count of frontier releases per quarter by lab.
Model release cadence by lab
Releases by quarter
Frontier-model releases per quarter, by lab, 2024 → 2026.
Releases by quarter
Rendering the interactive chart…
Expand data table
Benchmark score vs output-token price for leading models.
Capability vs cost
Capability vs cost
Artificial Analysis Intelligence Index vs output $/M tokens (June 2026 snapshot).
Capability vs cost
Rendering the interactive chart…
Expand data table
| Dimension | Series | Value | Value basis | Source |
|---|---|---|---|---|
| Claude Opus 4.8 | Benchmark score | 62 | Actual | Artificial Analysis: model intelligence & pricing |
| Claude Opus 4.8 | Cost per m tokens | 25 | Actual | Artificial Analysis: model intelligence & pricing |
| GPT-5.5 | Benchmark score | 60 | Actual | Artificial Analysis: model intelligence & pricing |
| GPT-5.5 | Cost per m tokens | 12 | Actual | Artificial Analysis: model intelligence & pricing |
| Gemini 3.1 Pro | Benchmark score | 57 | Actual | Artificial Analysis: model intelligence & pricing |
| Gemini 3.1 Pro | Cost per m tokens | 12 | Actual | Artificial Analysis: model intelligence & pricing |
| Claude Sonnet 4.6 | Benchmark score | 51 | Actual | Artificial Analysis: model intelligence & pricing |
| Claude Sonnet 4.6 | Cost per m tokens | 15 | Actual | Artificial Analysis: model intelligence & pricing |
Estimated training FLOP over time.
Training compute growth
Training compute
Estimated training compute of frontier models by year (Epoch AI).
Training compute
Rendering the interactive chart…
Expand data table
| Period | Series | Value | Value basis | Source |
|---|---|---|---|---|
| 2020 | Flops estimate | 3.1e+23 | Actual | Epoch AI: compute & training trends |
| 2022 | Flops estimate | 2.5e+24 | Actual | Epoch AI: compute & training trends |
| 2023 | Flops estimate | 2e+25 | Actual | Epoch AI: compute & training trends |
| 2024 | Flops estimate | 5e+25 | Actual | Epoch AI: compute & training trends |
| 2025 | Flops estimate | 5e+26 | Actual | Epoch AI: compute & training trends |
Caveat: Flop figures are third-party estimates (Epoch AI), not disclosed by labs.
Per-model risk-domain posture (blocked / gated / allowed).
Safety-gated capabilities matrix
Safety posture matrix
Editorial encoding of published model-safety policies (allowed / gated / blocked).
Safety posture matrix
Rendering the interactive chart…
Expand data table
| Dimension | Series | Value | Value basis | Source |
|---|---|---|---|---|
| Claude Fable 5 | Bio | 1 | Actual | Anthropic Model Cards & Release Notes |
| Claude Fable 5 | Chem | 1 | Actual | Anthropic Model Cards & Release Notes |
| Claude Fable 5 | Cyber | 1 | Actual | Anthropic Model Cards & Release Notes |
| Claude Fable 5 | Legal | 3 | Actual | Anthropic Model Cards & Release Notes |
| Claude Fable 5 | Medical | 2 | Actual | Anthropic Model Cards & Release Notes |
| Claude Opus 4.8 | Bio | 2 | Actual | Anthropic Model Cards & Release Notes |
| Claude Opus 4.8 | Chem | 2 | Actual | Anthropic Model Cards & Release Notes |
| Claude Opus 4.8 | Cyber | 2 | Actual | Anthropic Model Cards & Release Notes |
| Claude Opus 4.8 | Legal | 3 | Actual | Anthropic Model Cards & Release Notes |
| Claude Opus 4.8 | Medical | 2 | Actual | Anthropic Model Cards & Release Notes |
| Frontier baseline (typical) | Bio | 2 | Actual | Stanford HAI: AI Index Report |
| Frontier baseline (typical) | Chem | 2 | Actual | Stanford HAI: AI Index Report |
| Frontier baseline (typical) | Cyber | 2 | Actual | Stanford HAI: AI Index Report |
| Frontier baseline (typical) | Legal | 3 | Actual | Stanford HAI: AI Index Report |
| Frontier baseline (typical) | Medical | 2 | Actual | Stanford HAI: AI Index Report |
Caveat: Editorial 1=blocked / 2=gated / 3=allowed scale, a posture summary, not a measured benchmark.