Blog

Notes on open-source AI, model launches, and the tools we build at ChatOSS.

October 29, 202611 min read

MiniMax M3.1 Flash may be the best open-source orchestrator agent right now

AutomationBench is the closest public test of orchestration, and MiniMax M3.1 Flash wins it on both the independent run (73% vs 67%) and the vendors' table (62.8 vs 60.5). It also leads HLE in Artificial Analysis's run, 48% to 43% — but DeepSeek V4.1 Flash 1017 still owns coding, cache-heavy bills and the MIT licence. The honest case, including the numbers that cut against it.

MiniMax M3.1 FlashDeepSeek V4.1 Flash 1017Orchestrator AgentsAutomationBenchBenchmarksOpen Weight

October 27, 202610 min read

MiniMax M3.1 Flash vs. DeepSeek V4.1 Flash 1017: cheaper tokens, higher bill

Both list at $0.15/$0.60 per million tokens, and MiniMax wins the business-workflow benchmarks. But on vals.ai's Vibe Code Bench v1.1, DeepSeek's October 17 checkpoint scores 87.73% at $0.58 per test while M3.1 Flash scores 73.94% at $1.15 — because the cheaper token burns 66.86M of them per task. Here is the independent evidence and the cache-aware math.

MiniMax M3.1 FlashDeepSeek V4.1 Flash 1017Agentic CodingBenchmarksCost per TaskOpen Weight

September 21, 202611 min read

GLM 5.3 Flash vs. DeepSeek V4.1 Flash: which is better at agentic coding?

Both labs ship a million-token context, MIT weights, and a ~$0.15-per-million price tag. On the independent harnesses that have actually run both models — vals.ai's Vibe Code Bench and Terminal-Bench 2.1, BenchLM's Vibe Code Bench 1-100, and Artificial Analysis' v4.3 index — DeepSeek V4.1 Flash wins agentic coding, and by a wider margin than either vendor's own table suggests.

GLM 5.3 FlashDeepSeek V4.1 FlashAgentic CodingBenchmarksCost per TaskOpen Weight

September 10, 20269 min read

DeepSeek V4.1 Flash: Opus 5-tier agentic coding at 1/33 the price

DeepSeek's new ~748B-parameter Flash model (552B backbone + 196B Engram memory) retires V4 Pro, ships native vision, and — on DeepSeek's own max-effort numbers — edges Claude Opus 5 and GPT-5.6 Sol on Terminal-Bench 2.1 and DeepSWE v1.1 while costing $0.15/$0.60 per million tokens. Full benchmark table, pricing math, and where the closed frontier still wins.

DeepSeek V4.1 FlashClaude Opus 5GPT-5.6 SolBenchmarksOpen Weight

August 31, 202612 min read

GLM-5.3 and GLM-5.3 Flash: Z.ai's one-two punch matches Claude and GPT at a tenth of the price

Z.ai shipped a post-trained flagship (GLM-5.3) and a brand-new 320B multimodal sibling (GLM-5.3 Flash) two weeks apart. We benchmark both against Claude Opus 5, Fable 5, and GPT-5.6 Sol — with charts, a comparison table, and the pricing math.

GLM-5.3GLM-5.3 FlashClaude Opus 5GPT-5.6 SolBenchmarksOpen Weight

August 14, 20266 min read

One hour on DeepSeek V4 Pro cost $0.28. The same hour on Claude and ChatGPT: 68–136× more.

31.2 million input tokens, 107K output tokens, 157 API calls — and 28 cents. Here's the real billing-log breakdown, what the identical token volume would have cost on Claude Opus 5, GPT-5.6 Sol, and Claude Fable 5, and the two numbers I had wrong before I checked.

DeepSeek V4 ProGPT-5.6 SolClaude Opus 5Prompt CachingCost

August 13, 20268 min read

DeepSeek V4 Pro 0813: frontier-class benchmarks at 100× less than Opus 5

DeepSeek's flagship just went GA — and on SWE-bench Verified its open-weight scores match Anthropic's closed frontier while costing 10–100× less per task. Here's the full head-to-head with Opus 5, Fable 5, and GPT-5.6 Sol, with a price-vs-intelligence chart and comparison table.

DeepSeek V4 ProClaude Opus 5GPT-5.6 SolBenchmarksOpen Weight

August 5, 20267 min read

Did DeepSeek V4 Flash just dethrone GLM 5.2?

DeepSeek V4 Flash costs 10× less than GLM-5.2 and matches or beats it on several coding benchmarks. But GLM-5.2 still leads on broad intelligence and reasoning. Here’s the full head-to-head with charts and a comparison table.

DeepSeek V4 FlashGLM-5.2BenchmarksComparisonOpen Source

July 20, 20266 min read

Ollama Cloud shut down new Max plans — and Kimi K3 is melting the servers

Ollama paused new $100/mo Max subscriptions because cloud token volume is doubling every month. Kimi K3 just landed on the platform, GLM-5.2 forced a GPU doubling, and even Max users hit an “extra usage only” wall. Here's what's happening.

OllamaOllama CloudKimi K3GLM-5.2Open Source

July 20, 20267 min read

Kimi K3 vs. Fable 5 vs. GPT-5.6 Sol: the benchmark showdown

Three frontier models, one week of launches. We stack Kimi K3's open-weight numbers against Anthropic's Claude Fable 5 and OpenAI's GPT-5.6 Sol across intelligence, coding, context, and price — with charts.

Kimi K3Claude Fable 5GPT-5.6 SolBenchmarksComparison

July 20, 20264 min read

Is Kimi K3 down?

Moonshot AI's breakout open model isn't offline — but a record-breaking launch has pushed its compute to the limit, and new subscriptions are paused. Here's what's actually happening.

Kimi K3Moonshot AIOutageOpen Source