GLM-5.3
Unavailable in this round
Head-to-head comparison
GLM-5.3 vs. Mistral Large 3
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
- shared result series
- 6
- distinct benchmarks
- 6
- latest retrieval
- 2026-09-29
Change model selection
Specifications
General specifications
Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.
| Attribute | GLM-5.3 | Mistral Large 3 |
|---|---|---|
| Provider | Z.ai | Mistral AI |
| Released | Aug 18, 2026 | Dec 2, 2025 |
| Availability | Active | Active |
| Model type | Open Weights | Open Weights |
| Parameters | 744B, 40B active | 675B, 41B active |
| Architecture | Mixture of Experts | Mixture of Experts |
| Context window | 1,000,000 tokens | 262,144 tokens |
| Knowledge cutoff | Not published | Not published |
| Technical sources | Model, Context | Model, Context |
Pricing
API pricing compared
The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.
| Price type | GLM-5.3 | Mistral Large 3 |
|---|---|---|
| API input | $1.4 | $0.5 |
| API output | $4.4 | $1.5 |
| Cache read | $0.26 | Not listed |
| Cache write (5 min.) | Not listed | Not listed |
| Cache write (1 hr.) | Not listed | Not listed |
| Price verified | 09/22/2026 Source | 09/22/2026 Source |
GLM-5.3Mistral Large 3
API inputUSD per 1M tokens, base tier
GLM-5.3$1.4
Mistral Large 3Lower price$0.5
API outputUSD per 1M tokens, base tier
GLM-5.3$4.4
Mistral Large 3Lower price$1.5
Key to the marks:better valuebetter, but not conclusivetie
Pricing by provider
Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.
| Model | Provider | Purchase route and tariff | Input per 1M tokens | Output per 1M tokens | Source |
|---|---|---|---|---|---|
| GLM-5.3 | Z.ai | Direct from developerStandard API | $1.4 | $4.4 | Source09/22/2026 |
| AkashML | Via OpenRouterakashml/fp8 | $0.19 | $4.4 | Source10/15/2026 | |
| Alibaba | Via OpenRouteralibaba | $1.19 | $3.74 | Source10/15/2026 | |
| Alibaba | Via OpenRouteralibaba/prime | $2.8 | $8.8 | Source10/15/2026 | |
| AtlasCloud | Via OpenRouteratlas-cloud/fp8 | $1.4 | $4.4 | Source10/15/2026 | |
| Baidu | Via OpenRouterbaidu/fp8 | $1.4 | $4.4 | Source10/15/2026 | |
| BaseTen | Via OpenRouterbaseten/fast | $2.1 | $6.6 | Source10/15/2026 | |
| BaseTen | Via OpenRouterbaseten/fp4 | $1.4 | $4.4 | Source10/15/2026 | |
| BaseTen | Via OpenRouterbaseten/fp4/us | $1.4 | $4.4 | Source10/15/2026 | |
| BaseTen | Via OpenRouterbaseten/us/fast | $2.1 | $6.6 | Source10/15/2026 | |
| Cloudflare | Via OpenRoutercloudflare | $1.4 | $4.4 | Source10/15/2026 | |
| Crusoe | Via OpenRoutercrusoe/fp4 | $1.4 | $4.4 | Source10/15/2026 | |
| Decart | Via OpenRouterdecart/fp4 | $0.84 | $4.4 | Source10/15/2026 | |
| DeepInfra | Via OpenRouterdeepinfra/fp4 | $0.5625 | $2.5 | Source10/15/2026 | |
| DigitalOcean | Via OpenRouterdigitalocean | $0.91 | $2.86 | Source10/15/2026 | |
| Fireworks | Via OpenRouterfireworks | $1.4 | $4.4 | Source10/15/2026 | |
| Fireworks | Via OpenRouterfireworks/fast | $2.1 | $6.6 | Source10/15/2026 | |
| Friendli | Via OpenRouterfriendli | $1.26 | $3.96 | Source10/15/2026 | |
| GMICloud | Via OpenRoutergmicloud/fp8 | $0.98 | $3.08 | Source10/15/2026 | |
| Inceptron | Via OpenRouterinceptron/fp4 | $0.55 | Lowest listed price: $2.2 | Source10/15/2026 | |
| InferenceNet | Via OpenRouterinference-net/fp4 | $0.08 | $4.8 | Source10/15/2026 | |
| Io Net | Via OpenRouterio-net/fp8 | $0.49 | $2.9 | Source10/15/2026 | |
| Makora | Via OpenRoutermakora/fp4 | $0.14 | $4.4 | Source10/15/2026 | |
| Mistral | Via OpenRoutermistral/nvfp4 | $1.4 | $4.4 | Source10/15/2026 | |
| Mistral | Via OpenRoutermistral/nvfp4/eu | $1.54 | $4.84 | Source10/15/2026 | |
| Mistral | Via OpenRoutermistral/zdr | $1.4 | $4.4 | Source10/15/2026 | |
| Modal | Via OpenRoutermodal | $1.4 | $4.4 | Source10/15/2026 | |
| ModelRun | Via OpenRoutermodelrun/fp4 | $2.1 | $6.6 | Source10/15/2026 | |
| Morph | Via OpenRoutermorph/fp8 | $0.085 | $6 | Source10/15/2026 | |
| Novita | Via OpenRouternovita/fp8 | $0.7 | Lowest listed price: $2.2 | Source10/15/2026 | |
| Parasail | Via OpenRouterparasail/fp8 | $1.4 | $4.4 | Source10/15/2026 | |
| Phala | Via OpenRouterphala | $0.84 | $2.64 | Source10/15/2026 | |
| PrimeIntellect | Via OpenRouterprimeintellect | $1.4 | $4.4 | Source10/15/2026 | |
| Reka | Via OpenRouterreka | $0.14 | $4.2 | Source10/15/2026 | |
| Relace | Via OpenRouterrelace | Lowest listed price: $0.024 | $4.4 | Source10/15/2026 | |
| Sail Research | Via OpenRoutersail-research/fp8 | $0.15 | $3.4 | Source10/15/2026 | |
| Sail Research | Via OpenRoutersail-research/us | $0.15 | $3.4 | Source10/15/2026 | |
| SiliconFlow | Via OpenRoutersiliconflow/fp8 | $0.7 | Lowest listed price: $2.2 | Source10/15/2026 | |
| Tenstorrent | Via OpenRoutertenstorrent/fp8 | $0.6 | $2.5 | Source10/15/2026 | |
| Together | Via OpenRoutertogether | $1.4 | $4.4 | Source10/15/2026 | |
| Venice | Via OpenRoutervenice | $1.4 | $4.4 | Source10/15/2026 | |
| Wafer | Via OpenRouterwafer | $0.03 | $4.8 | Source10/15/2026 | |
| Wafer | Via OpenRouterwafer/us | $0.079 | $4.8 | Source10/15/2026 | |
| Z.AI | Via OpenRouterz-ai/fp8 | $1.4 | $4.4 | Source10/15/2026 | |
| Mistral Large 3 | Mistral AI | Direct from developerStandard API | Lowest listed price: $0.5 | Lowest listed price: $1.5 | Source09/22/2026 |
| Mistral | Via OpenRoutermistral/eu | $0.55 | $1.65 | Source10/15/2026 | |
| Mistral | Via OpenRoutermistral/zdr | Lowest listed price: $0.5 | Lowest listed price: $1.5 | Source10/15/2026 |
Performance
Shared benchmarks
Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.
Capability profile from matched benchmarks
Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.
GLM-5.3
Mistral Large 3
Coding: 100 / 56.1 (2 benchmark families)
Reasoning: 100 / 77.6 (1 benchmark family)
Knowledge: 100 / 92 (1 benchmark family)
Finance: 99 / 100 (1 benchmark family)
Legal: 100 / 93.3 (1 benchmark family)
6 matched rows from 6 benchmark families were considered. The radar shows 5 of 5 comparable categories.
GLM-5.3Mistral Large 3
GPQA DiamondOverall. Higher is better. No documented setup difference
GLM-5.3Winner88.132 %
Mistral Large 368.434 %
LegalBenchOverall. Higher is better. No documented setup difference
GLM-5.3Winner84.837 %
Mistral Large 379.138 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
GLM-5.3Winner80.535 %
Mistral Large 355.337 %
MMLU-ProOverall. Higher is better. No documented setup difference
GLM-5.3Winner86.77 %
Mistral Large 379.823 %
SWE-bench VerifiedOverall. Higher is better. No documented setup difference
GLM-5.3Winner95.4 %
Mistral Large 341.4 %
TaxEval v2Overall. Higher is better. No documented setup difference
GLM-5.372.363 %
Mistral Large 3Winner73.058 %
Key to the marks:better valuebetter, but not conclusivetie
| Benchmark and task | GLM-5.3 | Mistral Large 3 | Source |
|---|---|---|---|
GPQA DiamondOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | Winner88.132 % | 68.434 % | Vals AISource detailsData as of: 09/01/2026 |
LegalBenchOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | Winner84.837 % | 79.138 % | Vals AISource detailsData as of: 09/27/2026 |
LiveCodeBench v6OverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | Winner80.535 % | 55.337 % | Vals AISource detailsData as of: 09/01/2026 |
MMLU-ProOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | Winner86.77 % | 79.823 % | Vals AISource detailsData as of: 09/01/2026 |
SWE-bench VerifiedOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | Winner95.4 % | 41.4 % | Vals AISource detailsData as of: 09/01/2026 |
TaxEval v2OverallTest detailsNo documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better | 72.363 % | Winner73.058 % | Vals AISource detailsData as of: 09/01/2026 |
Key to the marks:better valuebetter, but not conclusivetie | |||
Our model tests
Our tests
SVG short test
One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.
Shared test round: 4ae5d8eeb9a9
Mistral Large 3
API request failed. The model was not evaluated.
Earlier tests
Pelican on a bicycle
A community classic for free-form SVG drawing.
GLM-5.3
Reasoning (requested): high
Current attempt
- Run date
- Oct 2, 2026
- API provider
- openrouter
- Requested API model
- z-ai/glm-5.3
- API model reported in response
- z-ai/glm-5.3
- Reasoning setting
- high
- Pinned endpoint
- Z.AI | z-ai/glm-5.3-20260816
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Passed, not a quality rating
- Response time
- 20.4 s
Visually reviewed. This individual test does not establish overall model quality.
Earlier attempts (2)
- Oct 1, 2026API request failedReasoning setting: high
- Sep 7, 2026API request failedReasoning setting: high
Mistral Large 3
Reasoning (model default): no reasoning mode Source
Current attempt
- Run date
- Oct 1, 2026
- API provider
- openrouter
- Requested API model
- mistralai/mistral-large-2512
- API model reported in response
- mistralai/mistral-large-2512
- Reasoning setting
- not specified
- Pinned endpoint
- Mistral | mistralai/mistral-large-2512
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Passed, not a quality rating
- Response time
- 14.2 s
Visually reviewed. This individual test does not establish overall model quality.
Earlier attempts (1)
- Sep 7, 2026API request failedReasoning setting: not specified
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)How to read this comparison
Winning one benchmark is not an overall verdict
Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.
The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.
Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.
More matchups
Related LLM comparisons
Compare GLM-5.3 and Mistral Large 3 with other leading models using the same data and benchmark logic.