Tag
SWE-Bench
SWE-bench is a benchmark for measuring whether models and coding agents can fix real GitHub issues end to end. Its variants, including Verified and Lite, are used to compare bug localization, test-driven edits, and the cost of agentic repair workflows.
15 articles
Benchmarks should not pick your LLM in 2026
Benchmarks matter, but they should not be the primary basis for choosing an LLM in 2026.
9 Cursor alternatives that beat lock-in
I break down 9 Cursor alternatives, why devs leave, and the free OSS stack I’d copy first.
Claude vs GPT vs Gemini: Coding Benchmark Leaderboard
A June 2026 coding benchmark comparison of Claude, GPT, and Gemini for model buyers.
AI Benchmarks 2026: Top Evaluations and Limits
MMLU, HLE, SWE-Bench and agent tests are hitting limits in 2026, while production gaps and contamination keep human review necessary.
MiMo-V2-Flash hits top open-source SWE-bench scores
Xiaomi’s MiMo-V2-Flash tops open-source SWE-bench scores while OpenRouter lists it at $0.10/$0.30 per 1M tokens.
Anthropic’s own data says AI is already building AI
Anthropic’s data shows AI is already accelerating AI development, and that should alarm every serious builder.
Kimi K2.6: What Changed in 2026
Kimi K2.6 is Moonshot AI’s open-weights flagship, with agent swarms, INT4 weights, and top-tier coding scores.
Kimi K2.6 and Qwen 3.6 Narrow the Gap
Kimi K2.6 and Qwen 3.6 are open-weight models that now rival closed models on coding and agent tasks.
How AI Agents Spend Your Money: 1000x Tokens on SWE-bench
A study of SWE-bench Verified shows agentic coding can consume 1000x more tokens than chat, with costs driven by inputs and hard to predict.
Qwen3.6-27B opens a smaller, sharper path to coding
Qwen3.6-27B is a 27B dense multimodal model that beats Qwen3.5-397B-A17B on key coding benchmarks while staying easier to deploy.
Claude Mythos Preview Tops GPT-5.4 on Key Benchmarks
Anthropic’s unreleased Mythos Preview beats GPT-5.4 and Gemini 3.1 Pro on coding, math, and agent tests, led by 97.6% on USAMO.
I Tested Devin on 10 Tasks. It Finished 3.
Devin scored 13.86% on SWE-bench and finished 3 of 10 real tasks in one test, showing where AI coding agents still fall short.
Gemini 3.1 Pro: Google’s new top model in numbers
Gemini 3.1 Pro posts 77.1% on ARC-AGI-2, 94.3% on GPQA Diamond, and a 1M-token context window, while keeping Gemini 3 pricing.
GLM-5: Z.AI's new flagship for coding and agents
GLM-5 posts 77.8 on SWE-bench Verified and 56.2 on Terminal Bench 2.0, putting Z.AI in direct competition with top coding models.
Xiaomi MiMo-V2-Pro: 1T MoE Model for Agents
Xiaomi’s MiMo-V2-Pro packs 1T parameters, 42B active, and 1M context, with SWE-bench results close to Claude Sonnet 4.6.