Quality
Known Good Index and the capability indices, side by side
Each index is min-max normalised across tracked models and scaled 0–100 from published evaluations. We do not run these evaluations.
| Metric | DeepSeek: R1 Distill Llama 70B | gpt-5.5-pre-release |
|---|---|---|
| Known Good Index | 52 | 98 |
| Mathematics Index | 71 | 100 |
| Science Index | 52 | 99 |
| Reasoning Index | 59 | — |
| Agentic Index | — | 94 |
| Openness Index | 60 | 5 |
Quality Breakdown
Every evaluation both models report a published score for
Bar = DeepSeek: R1 Distill Llama 70B · marker = gpt-5.5-pre-release · scores ingested from Epoch AI (CC-BY 4.0)
Right-hand figures read DeepSeek: R1 Distill Llama 70B / gpt-5.5-pre-release. DeepSeek: R1 Distill Llama 70B leads on 0 of 2, gpt-5.5-pre-release on 2.
Arena Elo
Human preference rating from blind pairwise votes
Elo from blind pairwise votes, ingested from Arena. Higher is better.
Neither model currently appears in an arena we ingest.
Price & Cost
Published API pricing by token type
USD per 1M tokens. Blended is a 3:1 input:output mix. Live from OpenRouter, cross-checked against models.dev. Lower is better.
| Metric | DeepSeek: R1 Distill Llama 70B | gpt-5.5-pre-release |
|---|---|---|
| Input $/1M | $0.80 | — |
| Output $/1M | $0.80 | — |
| Blended $/1M | $0.80 | — |
| Cache read $/1M | — | — |
Context Window
Maximum input accepted and maximum output emitted
Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.
| Metric | DeepSeek: R1 Distill Llama 70B | gpt-5.5-pre-release |
|---|---|---|
| Context window | 8k | — |
| Max output tokens | 8k | — |
Speed & Latency
Median throughput and time to first token across hosting providers
Medians across all tracked providers, derived from OpenRouter endpoint telemetry.
| Metric | DeepSeek: R1 Distill Llama 70B | gpt-5.5-pre-release |
|---|---|---|
| Output tokens/s | 24 | — |
| Time to first token | 0.8s | — |
Providers
Which hosts serve each model, and at what price and speed
| Provider | DeepSeek: R1 Distill Llama 70B blended | DeepSeek: R1 Distill Llama 70B tok/s | gpt-5.5-pre-release blended | gpt-5.5-pre-release tok/s |
|---|---|---|---|---|
| Novita | $0.80 | 27 | — | — |
Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.