xLAM 2 3B

Not independently scored by Artificial Analysis

A 3B from Salesforce trained specifically for function calling, not for general chat. It is one of the reference models on the BFCL leaderboard, which is why we measure it: it tells us how far a general-purpose model of the same size is from one built for the job.

BigCodeBench-Hard pass@1 9% (13/148), via official protocol · llama.cpp Q8_0 · one request at a time · a shared cluster GPU · mean of 6 runs, range 0.0 pp. The brutal counterpart to HumanEval — where HumanEval saturates near the top, BCB-Hard spreads the field, so this is the number that actually separates coding ability.

We have not been able to tie these files back to a published repo, so take the quant names as the labels we ran them under. Every point measured on the same class of card, one pass, one request at a time. One problem is 0.68 points, so anything under ~3.4 points apart is a tie — that is the spread we measure between GPU classes, and our rows are not all on the same card. Each card column is the context left for the KV cache after the weights, KV-Q4 / KV-Q8. A dash means the file does not fit that card, or fits with no room left to work. Context is usually the real constraint, not quality. Computed for one slot (--parallel 1), which is what you get serving yourself. llama-server opens four by default, and on a hybrid that costs real context — the table below each curve shows how much. The card figures assume a dedicated card. Measured on an idle one: the driver keeps 623 MiB of 143,771, so 99.6% is usable. Compute buffers are measured too — a fixed ~130 MiB plus 1 MiB per 1K of context, the same slope on every architecture we checked. If your card also runs your desktop you get noticeably less, and we have not measured that case yet.

83.7% ± 2.4 over 1150 problems

F16 · a shared cluster GPU · KV f16 · 2 runs · spread between runs 0.00 points. This is the non-agentic half of BFCL: does the model call the right function with the right arguments. It says nothing about how it behaves over a long agentic conversation, which is a separate measurement. The score is BFCL’s own: the unweighted mean of four groups (simple, multiple, parallel, parallel multiple), where simple is itself the mean of Python, Java and JavaScript. Every group counts the same whatever its size, and irrelevance detection — which we also measure, another 240 problems — is not part of it. The margin follows that same weighting.

All 13 RULER tasks, one request at a time, KV cache f16, bench commit c3f5e3b4, seed 42. The score is the mean of the 13; the margin is two standard deviations of the sampling, so it grows as the sample shrinks and as the score drops.

This is not a coding score and must not be read as one. RULER asks whether the model finds and follows a fact buried in a long text. Quantising hits the two differently, so a model that still retrieves at length may already have lost the code.

Use it for tool routing, not for writing. At F16 it needs about 8 GB, so it fits any card we test on.