THE SOURCE IN CONTEXT
The dated comparison contains 33 valid full deployment runs of v7.0, with 80 scenarios across 13 domains and two repeated seeds. A row identifies a model, quantization, engine/recipe, hardware and thinking mode. TrueScore is the project’s suite score, not a percent-correct rate and not a measure of generation speed.
What is the unit of this quality cohort?
The dated comparison contains 33 valid full deployment runs of v7.0, with 80 scenarios across 13 domains and two repeated seeds. A row identifies a model, quantization, engine/recipe, hardware and thinking mode. TrueScore is the project’s suite score, not a percent-correct rate and not a measure of generation speed.
Source: Weschera · pinned document
Why retain thinking mode and deployment identity?
The GLM Flash example is 88.9 with thinking enabled and 84.8 with thinking disabled under the named two-Spark EXL3/TensorFold recipe. Those are two source rows, not a general estimate of the value of reasoning across all tasks or runtimes. Different quantizations, engines or hardware in other rows create additional differences.
Source: Weschera · pinned document
How are incomplete and failed runs handled?
The cohort requires its golden gate and a transport-error limit below five percent. Three hosted runs each had one timeout. The document excludes incomplete runs and describes reasoning-channel parsing failures separately. Counting only the successful top-line score would discard information the author deliberately retained about the evaluation process.
Source: Weschera · pinned document
What comparisons are unsupported?
The author says v7 is not comparable with v6.x and notes that easy shared scenarios compress the upper scores. Hosted APIs have uncontrolled hardware and network latency. This page therefore excerpts two contextual examples rather than republishing the full leaderboard or converting it into a site-wide ranking. No license declaration was found in repository metadata; the original report remains the full source.
Source: Weschera · pinned document
Reported figures and their conditions
Selected facts reported by the original author. Each row has its own configuration and measurement boundary. Run AI Here has not reproduced these tests.
| Configuration / workload | Metric | Reported value | Evidence |
|---|---|---|---|
| GLM-5.3 Flash, thinking on | TrueScore | 88.9 suite scorereported value | Original row ↗ |
| GLM-5.3 Flash, thinking off | TrueScore | 84.8 suite scorereported value | Original row ↗ |
GLM-5.3 Flash, thinking on · TrueScore · conditions
| system | DGX Spark / Mac Studio / hosted APIs, per row |
|---|---|
| node_count | Not specified |
| parallelism | Not specified |
| kv_dtype | Not specified |
| context_limit_tokens | Not specified |
| experiment_date | 2026-10-12 |
| suite | v7.0 full, 80 scenarios / 13 domains |
| repetitions | 2 |
| seeds | [2001, 2002] |
| sampling | model-card settings |
| output_budget | uncapped within each deployment context |
| hardware | 2 Sparks TP2 |
| quantization | EXL3 4bpw |
| runtime | TensorFold v0.6.0 + DFlash2, Mia recipe v1.8 |
| thinking | True |
GLM-5.3 Flash, thinking off · TrueScore · conditions
| system | DGX Spark / Mac Studio / hosted APIs, per row |
|---|---|
| node_count | Not specified |
| parallelism | Not specified |
| kv_dtype | Not specified |
| context_limit_tokens | Not specified |
| experiment_date | 2026-10-12 |
| suite | v7.0 full, 80 scenarios / 13 domains |
| repetitions | 2 |
| seeds | [2001, 2002] |
| sampling | model-card settings |
| output_budget | uncapped within each deployment context |
| hardware | 2 Sparks TP2 |
| quantization | EXL3 4bpw |
| runtime | TensorFold v0.6.0 + DFlash2, Mia recipe v1.8 |
| thinking | False |
AI-assisted source reading and original editorial synthesis; no independent model execution.