Head-to-head The same models run on Ollama and OpenCode — who streams faster? See the race on TokenDyno →

Methodology

Every number on this site comes from a reproducible automated benchmark. This page documents exactly what we measure, how we measure it, and what we do not claim.

What one benchmark run looks like

The worker sends a single streaming chat-completion request to the provider's OpenAI-compatible API endpoint. The model is asked to write a 400-word prose explanation of HTTP request routing. max_tokens is capped at 300 — enough to produce a full streaming response without waiting for a very long generation, and consistent across every model so comparisons are fair. The prompt and cap are fixed; they never change between runs.

Anatomy of one benchmark run A timeline of a single streaming request. The request is dispatched at time zero. The gap until the first non-empty content chunk arrives is TTFT, time to first token, which covers network round-trip and the provider's prompt processing. The remaining span, from the first token until generation stops, is the generation window. Tokens per second is the token count divided by that generation window, so TTFT is excluded from the throughput figure. Generation stops at the 300-token cap, or at the 120-second timeout, whichever comes first. TTFT generation window request dispatched first token generation stops one tick = one output token 300-token cap or 120 s timeout, whichever is first TPS = tokens ÷ generation window TTFT is excluded — it is reported separately
Anatomy of one benchmark run. TTFT covers the network round-trip and the provider's prompt processing, up to the first non-empty content chunk. TPS divides the token count by the generation window that follows, so a slow queue lowers TTFT's score without flattering throughput — the two numbers stay independent. Generation stops at the 300-token cap or the 120-second timeout, whichever comes first.

TTFT — time to first token

TTFT (milliseconds) is measured from the moment the HTTP request is dispatched to the moment the first non-empty content chunk arrives in the stream. It captures network round-trip plus the provider's prompt-processing time. It does not include DNS or TLS handshake if a keep-alive connection is reused, but those costs are typical of real API usage.

TPS — tokens per second

TPS measures generation throughput — how fast the model emits output tokens, excluding the initial wait (TTFT).

For Ollama Cloud we use the server's own reported timing rather than measuring token arrival on our end. Each response includes eval_count (tokens generated) and total_duration (total server-side time). We compute:

TPS = eval_count ÷ (total_duration − time_to_first_token)

Reading the server's timing makes the number immune to network jitter and token buffering — some models stream their whole answer in a burst, which would wildly inflate a naïve client-side stopwatch. Subtracting time-to-first-token isolates generation from prompt processing and queueing. A run is discarded as malformed if the server returns no token count or generation time.

Timeout

Each request has a hard timeout of 120 seconds. If no complete response arrives in that window the run is recorded as a timeout error and counted against reliability.

Error taxonomy

Every failed run is classified into one of seven error kinds:

Failed runs are stored with ok = false and excluded from TPS and TTFT statistics. They are counted in the reliability percentage (success rate = successful runs ÷ total runs in the window).

Benchmark cadence

The worker runs benchmarks continuously using a round-robin priority queue. Each (provider, model) pair has a provider-specific target interval. Ollama Cloud Pro is sampled about every 10 minutes, while Ollama Free is sampled about every 60 minutes so the weekly free-tier balance lasts across all 21 supported models. Models that Ollama bills as extra usage rather than plan usage — currently Kimi K3 — are sampled about every 4 hours, because each of those runs is charged per token against a prepaid balance. The scheduler always picks the most-overdue pair next, so the order naturally staggers across models without fixed cron slots.

Circuit breaker: if a model records 3 consecutive failures, it is dropped to 30-minute probe intervals until it recovers (a successful run resets the counter). This prevents a failing model from flooding the queue.

Rate-limit backoff: a 429 response pushes that provider's next benchmark slot back by 5 minutes, giving the provider time to recover without hammering a quota.

Data retention

Chart windows pick the right table automatically: 24 h and 7 d windows use raw samples; 30 d and 1 y windows use hourly or daily rollups.

Reasoning mode

Some Ollama Cloud models support extended thinking (reasoning) via the native think API parameter. When a model advertises the thinking capability (/api/show), we benchmark with reasoning enabledthink: true for most models, or the effort level that matches the linked Artificial Analysis entry (e.g. think: "high" for gpt-oss, which AA scores as the high-effort variant). Models without the thinking capability are benchmarked as a single endpoint with no think parameter.

On the leaderboard, model names are suffixed with (non-reasoning) when our benchmark and Intelligence Index refer to AA's non-reasoning variant. Reasoning models are shown without an extra label — the default case.

Plan tiers — what we actually benchmark

Provider pricing tiers can change the models available and the speed a given model runs at. We benchmark on the following plans:

If you are on a free or lower tier you may see different throughput. Our numbers are not a ceiling — they reflect our specific plan and the state of the provider's infrastructure at measurement time.

Sequential, not parallel

Benchmarks run sequentially — one request at a time, waiting for the full response before the next. This mirrors realistic single-client usage and avoids inflating TPS numbers by running requests in parallel (which would share provider capacity).

What we do not claim

Open questions and feedback

If you notice a measurement that looks wrong, or want to suggest an improvement to the methodology, open an issue or start a discussion in the project repository. Accuracy and transparency are the point.

Frequently asked questions

How is LLM inference speed (tokens per second) measured?

Tokens per second is generation throughput: output tokens divided by the time spent generating them, excluding the initial wait for the first token. Ollama TPS uses the server's own reported timing (eval_count divided by total_duration) rather than a client-side stopwatch, so the number is immune to network jitter and token buffering. Time to first token is reported separately, because a fast generation rate behind a slow first token still feels slow.

How many tokens per second is a good speed for an LLM?

It depends on the task, and we deliberately do not publish a threshold we cannot measure. What we can say from our own data: the Ollama Cloud catalogue spans roughly an order of magnitude in measured throughput at any given moment, so the practical question is not "is this fast" but "which model is fastest right now for the work I am doing". The live leaderboard answers that, and it is re-measured about every 10 minutes on Ollama Pro.

Why measure tokens per second rather than total response time?

Total response time conflates two independent things: how long the model takes to start (time to first token) and how fast it produces text once started (tokens per second). They have different causes and different fixes, and a model can be good at one and bad at the other. We report both separately for every model rather than collapsing them into a single figure.