GLM-5.3 vs GPT-6.1 Sol
GLM-5.3 and GPT-6.1 Sol are within three points on the Models at Work leaderboard, which we treat as a tie (81 vs 81). GLM-5.3 is about 1.9× cheaper per blended million tokens ($2.15 vs $4). On Artificial Analysis' independent Intelligence Index, GPT-6.1 Sol leads 52 to 45.
| GLM-5.3 · Z.ai | GPT-6.1 Sol · OpenAI | |
|---|---|---|
| Leaderboard rank | #5 | #6 |
| Score (0–100) | 81 | 81 |
| Tier | Open weights | Workhorse |
| Price per 1M tokens | $1.40 in · $4.40 out | $2 in · $10 out |
| Context window | 1M | 1M |
| Open weights | Yes | No |
| Artificial Analysis Intelligence Index | 45 | 52 |
| Arena Text score | 1478 (rank 27) | — |
| Scale SWE-Bench Pro V2 (mini-swe-agent) | 84.30% | — |
| Scale MCP Atlas | 84.20 | — |
| Arena WebDev score | 1622 (rank 22) | — |
| Humanity's Sixth Sense (Scale) | — | 46.6 |
| Best for | Agentic coding in Claude Code / Pi-style harnesses, Security research and code auditing, Self-hosted frontier-ish reasoning | OpenAI-standardised teams, Agents API and Decisions API, Cost-controlled reasoning |
Choose GLM-5.3 if…
- you need agentic coding in claude code / pi-style harnesses
- you need security research and code auditing
- you need self-hosted frontier-ish reasoning
The open model people actually ship coding agents on. Same 744B base as GLM-5.2 with heavy agentic post-training; drops into Claude Code harnesses and holds its own on SWE-Bench Pro V2 and MCP Atlas at a third of frontier prices.
Caveats: License is muddled: AA lists a custom 'GLM-5.3 License' with commercial restrictions while Arena lists MIT. Read it before you self-host. Permissive on offensive-security tasks; that is a feature for red teams and a governance problem for everyone else. Open weights shipped ~2 weeks after the API; HN worried the public weights were safety-tuned differently.
Choose GPT-6.1 Sol if…
- you need openai-standardised teams
- you need agents api and decisions api
- you need cost-controlled reasoning
Near-Astra intelligence at a fifth of the price, which is OpenAI's own line and, for once, the index agrees.
What practitioners say
GLM-5.3: One of the biggest HN launches of the year (1,171 points, 584 comments). Practitioners report it 'fits Claude Code as its own, zero issues', that '$5 in tokens' of Claude work costs '$0.50' on GLM via Pi, and that it 'routinely finds bugs missed by Fable and Sol' in audits. The cyber angle was the controversy: users bragged about adapting kernel exploits that 'Claude and Opus outright refused', and others flagged the risk of nerfed public weights.
GPT-6.1 Sol: The launch thread's title did the arguing: 'near-Astra for a fifth of the price' drew 955 comments, most of them about routing.
Questions people ask
Which is better, GLM-5.3 or GPT-6.1 Sol?
GLM-5.3 and GPT-6.1 Sol are within three points on the Models at Work leaderboard, which we treat as a tie (81 vs 81). GLM-5.3 is about 1.9× cheaper per blended million tokens ($2.15 vs $4). On Artificial Analysis' independent Intelligence Index, GPT-6.1 Sol leads 52 to 45.
When should I choose GLM-5.3 over GPT-6.1 Sol?
Choose GLM-5.3 for agentic coding in claude code / pi-style harnesses, security research and code auditing, self-hosted frontier-ish reasoning. The open model people actually ship coding agents on. Same 744B base as GLM-5.2 with heavy agentic post-training; drops into Claude Code harnesses and holds its own on SWE-Bench Pro V2 and MCP Atlas at a third of frontier prices.
When should I choose GPT-6.1 Sol over GLM-5.3?
Choose GPT-6.1 Sol for openai-standardised teams, agents api and decisions api, cost-controlled reasoning. Near-Astra intelligence at a fifth of the price, which is OpenAI's own line and, for once, the index agrees.
Which is cheaper, GLM-5.3 or GPT-6.1 Sol?
GLM-5.3 costs $1.40 per million input tokens and $4.40 per million output tokens on Z.ai's list price (Z.ai Pricing, read Oct 11, 2026). GPT-6.1 Sol costs $2 per million input tokens and $10 per million output tokens on OpenAI's list price (OpenAI API pricing, read Oct 11, 2026).
Scores come from the Models at Work leaderboard: Score is 0 to 100 and computed, not typed: 55% independent evals (Artificial Analysis, Arena, Scale SEAL, Epoch, each scaled against its natural floor and the best score in this table, then averaged), 15% blended price on a fixed log scale ($0.05 per million is 100, $60 is 0), 15% practitioner sentiment from Signals and community threads, 15% operational fit (context window, open weights). A missing component drops out and the rest are reweighted. A model with no independent eval yet is provisional and ranks below every measured one. Within three points is a tie. Vendor-published figures are labelled and never counted. Prices are vendor list prices where published; blended figures assume three input tokens per output token.