Which model should you run on the iPhone 17 Pro? Announcing our new intelligence and inference testing for small models on mobile devices: independent measurement of how capable small models are in typical on-device tasks, and how they perform on popular phones - in partnership with @liquidai We have partnered with @liquidai to deliver mobile device inference benchmarking, covering a range of models in 4-bit or lower precision on the iPhone 17 Pro and Galaxy S26 Ultra We’re publishing our phone-scale intelligence evaluation results in combination with @liquidai's inference performance benchmarks to give users and developers a holistic view of how small models are performing on phones Inference benchmarking is conducted in a controlled environment using Liquid AI’s inference benchmarking software, which Artificial Analysis has examined and is open-sourced on Liquid AI’s GitHub. Results cover end-to-end generation time, output speed, peak memory usage and other metrics. The inference benchmarking app, ‘Pipette’, is available to download for free on iOS and Android, allowing users to test a variety of models on their own devices We are ranking phone-scale model intelligence based on each model’s average score in five evaluations chosen for the task-based work these models do in practice: BFCL, IFBench, AA-Omniscience, GPQA Diamond and MATH-500. These evaluations are run by Artificial Analysis using our independent methodology. By default, we limit models to 16K context on each of these evaluations, representing the lack of memory space for significant KV cache on mobile devices. This leads to some intelligent but verbose models dipping in relative score - they were not designed for the constraints that phone memory imposes on token use We are defining our portable device category as including models that fit within 8 GB of memory after quantization, including KV cache, at 8K context We expect both the intelligence and inference benchmarks to evolve over time, as new models, devices, inference frameworks and quantization techniques are released. Our pages will remain up to date with these new additions Initial results: ➤ Nanbeige4.2-3B and LFM2.5-2.6B share the top average evaluation score at 63 (with a 16K context limit), ahead of Ornith-1.0-9B at 62 and Qwen3.5 9B (Reasoning) at 61. LFM2.5-2.6B achieves its score more efficiently: on an iPhone 17 Pro it answers a standard 1,024-token prompt in 8.0s using 2.3 GB of memory, against 21.4s and 4.0 GB for Nanbeige4.2-3B and 25+ seconds and 6.9 GB for the two 9B models ➤ The 16K context limit shapes the leaderboard: as an example, Qwen3.5 9B (Reasoning) spends 74.5M output tokens across one pass of the benchmark set, hitting the 16K limit on 29% of its generations and landing in fourth place overall. With the limit raised to 64K, Ling 3.0 Tiny takes first place with a score of 66, ahead of Nanbeige4.2-3B (65), Qwen3.5 9B (Reasoning, 64), and LFM2.5 2.6B (64). But a 64K window does not fit in mobile phone memory, and at 55 output tokens/s on an iPhone, generating 64K tokens could mean a 20+ minute wait and a lot of battery use. This is why our primary results are capped at 16K, but we're also publishing a set of results capped at 64K, and another capped at one minute of generation time ➤ The speed-intelligence Pareto frontier is short: six models are unbeaten on both intelligence and speed on an iPhone 17 Pro: LFM2.5-230M (27 at 0.9s), MiniCPM5-1B (45 at 2.9s), LFM2.5-8B-A1B (58 at 5.7s), Ling 3.0 Tiny (59 at 5.7s), LFM2.5-2.6B (63 at 8.0s) and Nanbeige4.2-3B (63 at 21.4s). LFM2.5-8B-A1B and Ling 3.0 Tiny are mixture-of-experts models that activate ~1B parameters per token, which is how they answer in under 6s with 8B-class weights ➤ Leading models have opposite strengths: Nanbeige4.2-3B is the most balanced (76% on BFCL, 96% on MATH-500, 67% on GPQA Diamond); Qwen3.5 9B (Non-reasoning) is the strongest tool caller (77% on BFCL) and scientific reasoner (79% on GPQA Diamond); LFM2.5-2.6B follows instructions best of any model measured on the iPhone (59% on IFBench), clears 90% on MATH-500 and hallucinates far less on AA-Omniscience (79% non-hallucination, against 33% for Nanbeige4.2-3B and 24% for Qwen3.5 9B (Reasoning)) More details below in thread ⬇️

Today we release Pipette, a model evaluation suite for on-device intelligence, in partnership with @ArtificialAnlys Most benchmarking platforms are optimized to measure core capabilities and speed profile of foundation models served in the cloud. Pipette gives the field a common, reproducible way to measure the quality, speed, latency, and memory use of AI models on devices such as phones, laptops, PCs, AI boxes, and embedded hardware. > Pipette is open source > In Pipette, models get compated as model + quantization + runtime + device from one interface. > It comes with a warehouse of verified benchmark results, currently with 10k+ results across 35 model classes, 7 quants, llama.cpp runtimes, and 4 devices. > Pipette is a dynamic platform, allowing new contributions from day one, adding new devices, runtimes, model families, and quantization levels. 🧵

Today, we release DSpark draft models for LFM2.5-1.2B-Instruct, LFM2.5-2.6B, and LFM2.5-8B-A1B. These add a speculative decoding path that trades a minimal memory increase for a large decoding speedup without changing output quality. A lightweight draft model proposes a block of candidate tokens and the target model verifies them in a single forward pass. Across MATH500, GSM8K, HumanEval, MBPP, and MT-Bench at batch size 1: > Up to 3.18x throughput on an H100: LFM2.5-8B-A1B on MATH500, 428 → 1362 tok/s > Up to 2.87x on an M4 Max MacBook Pro: LFM2.5-1.2B-Instruct on HumanEval, 136 → 389 tok/s > LFM2.5-2.6B means: 2.67x on the H100 (323 → 864 tok/s), 2.27x on device (61 → 139 tok/s) > Under greedy decoding, the emitted sequence is identical to baseline by construction, so benchmark accuracy is unchanged. Each draft model is around 300M parameters, with embedding and LM head tied to its target model. The gain shows most in agentic workloads, where the model reasons before every tool call and the user waits through it all: on BFCL multi-tool scenarios, DSpark cuts LFM2.5-2.6B latency by nearly 50% on average. 🧵

Can coding agents autonomously solve a production-grade problem from scratch? Last year, we tasked two agents to build a BPE tokenizer trainer with time limits. Both zero-shot a working toy trainer in 30 minutes. Neither scaled to production. We then changed the setup with loops. Loops allowed us to iterate against real production data at scale. The correctness was verified with two independent libraries whose results the agent could not manipulate. The result of this experiment is a tokenizer trainer called toktoktok. Read more: Source:

We asked an unreleased research version of Claude to take a stab at the Riemann hypothesis. It didn’t solve it, but it did make strides on a related problem: it increased the lower bound for the fraction of zeros of the Riemann zeta function that satisfy the hypothesis from 41.6% to 67.2%.