Benchmark score vs output-token price for leading models.
Capability vs cost
Takeaway: The frontier moves down-and-right: same capability gets cheaper each generation.
Capability vs cost
Artificial Analysis Intelligence Index vs output $/M tokens (June 2026 snapshot).
Takeaway: The frontier moves down-and-right: same capability gets cheaper each generation.
Capability vs cost
The frontier moves down-and-right: same capability gets cheaper each generation.
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 |
Data table
Download CSV| Model | Series | Source | Value basis | Benchmark score | Cost per m tokens |
|---|---|---|---|---|---|
| Claude Opus 4.8 | capability_cost | Artificial Analysis: model intelligence & pricing | Actual | 62 | 25 |
| GPT-5.5 | capability_cost | Artificial Analysis: model intelligence & pricing | Actual | 60 | 12 |
| Gemini 3.1 Pro | capability_cost | Artificial Analysis: model intelligence & pricing | Actual | 57 | 12 |
| Claude Sonnet 4.6 | capability_cost | Artificial Analysis: model intelligence & pricing | Actual | 51 | 15 |
How this evidence was built
What it measures
Source-backed values are seeded for four of the five charts: the release cadence by lab (2024 → 2026, from each lab’s release notes), the capability-vs-cost scatter (Artificial Analysis Intelligence Index vs output $/M tokens, June 2026 snapshot), training-compute growth by year (Epoch AI, corroborated by Stanford hai), and a safety-gated capabilities matrix.
How it is calculated
- This is an interpretation of each model’s published safety policy, not a measured benchmark.
- Placeholder: the per-lab benchmark-trajectory chart is left unseeded, a consistent historical per-quarter, per-lab benchmark series was not sourceable without mixing incompatible benchmarks.
Key context
- Every numeric point carries a source citation and a basis label.
- Sources are each lab’s own model cards/release notes, Artificial Analysis, Epoch AI, and Stanford hai: cross-checked against public release timelines.
- Editorial encoding: the safety-gated matrix scores each model × domain as 3 = allowed / 2 = gated / 1 = blocked.
Key numbers
- Four labs trade the lead quarter to quarter: releases are clustered, not steady (anthropic-news / openai-research / google-deepmind / meta-ai).
- A leading model tops the Artificial Analysis Intelligence Index at ~62 while costing ~$25/M output tokens, capability up, price-per-capability down (artificial-analysis).
- Training compute scales off a ~3.1e23-flop gpt-3 (2020) baseline (epoch-ai, corroborated by Stanford hai).
- The safety matrix shows hard limits blocking high-risk cyber/bio/chem while gating legal/medical use, an editorial, not measured, scale (anthropic-news).
Caveats
Caveat: Flop figures are third-party estimates (Epoch AI), not disclosed by labs.
Caveat: Editorial 1=blocked / 2=gated / 3=allowed scale, a posture summary, not a measured benchmark.
Do not use this to
- 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).
Scope
June 2026
Sources
Last verified 10 Sept 2026