modelbench日本語

GLM-5.3-Flash

Z.aiCurrent

Input price
—
Per 1 million tokens (USD)
Output price
—
Per 1 million tokens (USD)
Effort levels
3total
Default: Max
Benchmark results
8total
Benchmark types: 8

Model information

API model ID
glm-5.3-flash
release date
Unknown
effort
Low / High / Max (default)
Effort source
Based on the Note in the HF model card for GLM-5.3-Flash (zai-org/GLM-5.3-Flash): reasoning_effort is low, high, max, with max as default. Mistral reasoning documentation also gives low, high, max for GLM 5.3 Flash (none is not supported). An official statement of the release date has not been confirmed.
Claude Code
unavailable
Codex
unavailable
Availability notes
Both are false because the model appears in neither the Claude Code official model list (code.claude.com/docs/en/model-config alias table, retrieved 2026-11-13; original: the table for "Use a model alias to select model settings without remembering exact version numbers" contains only Anthropic models such as fable, sonnet, opus, and haiku) nor the Codex official model list (learn.chatgpt.com/docs/models, retrieved 2026-11-13; original: "Recommended models" contains only the GPT-6 series) (connections via a custom provider are not counted as official options, and connections via a gateway are not counted as official options).
Availability source
https://code.claude.com/docs/en/model-config

Price (USD per 1 million tokens)

Prices do not vary by effort; token consumption does.

input—
output—
cache read—
cache write—

Not collected.

Benchmark results

BenchmarkeffortScoreSource cost (metric)measured/reported bysourceConditions and extraction method
DeepSWE v1.1not statednot stated63.4%—Z.aiGLM-5.3-Flash (Z.ai docs)official · Retrieved 2026-11-13Vendor-reported value (self-reported by Z.ai). Value in the main text. Evaluation conditions are from the Footnotes of the HF card (zai-org/GLM-5.3-Flash, MIT) for the same announcement. Effort not stated (recommended setting: reasoning_effort: max). mini-swe-agent harness; 6h timeout.transcribed from text
Source excerptGLM-5.3-Flash … 63.4 … on DeepSWE v1.1Location Text in the "Competitive Performance at Flash Cost" section of the docs.z.ai GLM-5.3-Flash page. Conditions: HF card Footnotes, DeepSWE (We run DeepSWE using the mini-swe-agent harness)
GPQA DiamondMax (default)Max90.2%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "GLM-5.3-Flash (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptgpqa_diamond.csv: Model version=glm-5.3-flash_max, Best score (across scorers)=0.9015151515151515, stderr=0.017183231147411448, Started at=2026-08-26T22:26:55.000ZLocation gpqa_diamond.csv, data row 69 (file lines 120-122; multi-line record), id=Jvt5BNr4ERbE9QGgMcEbmT, Model version=glm-5.3-flash_max
FrontierMath Tiers 1-3(v2)Max (default)Max55.8%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tiers_1_3_v2.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "GLM-5.3-Flash (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptfrontiermath_tiers_1_3_v2.csv: Model version=glm-5.3-flash_max, Best score (across scorers)=0.5578947368421052, stderr=0.029469977528223976, Started at=2026-08-27T13:29:52.000ZLocation frontiermath_tiers_1_3_v2.csv, data row 75 (file lines 99-101; multi-line record), id=YC2u9wykbYQg4gdkf76j26, Model version=glm-5.3-flash_max
FrontierMath Tier 4(v2)Max (default)Max17.1%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "GLM-5.3-Flash (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptfrontiermath_tier_4_v2.csv: Model version=glm-5.3-flash_max, Best score (across scorers)=0.17073170731707318, stderr=0.05949419959829495, Started at=2026-08-27T13:29:52.000ZLocation frontiermath_tier_4_v2.csv, data row 29 (file lines 60-62; multi-line record), id=iCysWvFJevNyw2dbYosU6J, Model version=glm-5.3-flash_max
OTIS Mock AIME 2024-2025Max (default)Max93.9%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, otis_mock_aime_2024_2025.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "GLM-5.3-Flash (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptotis_mock_aime_2024_2025.csv: Model version=glm-5.3-flash_max, Best score (across scorers)=0.9388888888888889, stderr=0.021622267380853318, Started at=2026-08-26T22:26:55.000ZLocation otis_mock_aime_2024_2025.csv, data row 77 (file lines 135-137; multi-line record), id=NCikvVWc5SEyMEbCqvVNb2, Model version=glm-5.3-flash_max
Chess Puzzles(Epoch AI)Max (default)Max21.0%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, chess_puzzles.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "GLM-5.3-Flash (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptchess_puzzles.csv: Model version=glm-5.3-flash_max, Best score (across scorers)=0.21, stderr=0.040936018074033236, Started at=2026-10-13T15:54:34.000ZLocation chess_puzzles.csv, data row 33 (file lines 69-71; multi-line record), id=fWNxmiSUC7BX8whqvzssY8, Model version=glm-5.3-flash_max
Epoch Capabilities Index(ECI)not statednot stated153.82—Epoch AIEpoch AI, epoch_capabilities_index/eci_scores.csv (CC BY 4.0)third-party · Retrieved 2026-11-12A per-model metric that combines results across multiple benchmarks and multiple efforts (not per effort). Calculated by Epoch AI.transcribed from table
Source excerpteci_scores.csv: Model=GLM-5.3-Flash, eci=153.82, eci_ci_low=152.0, eci_ci_high=155.78Location epoch_capabilities_index/eci_scores.csv, data row 52 (file line 53), Model=GLM-5.3-Flash
AutomationBench v1.0.6not statednot stated48.8%—Z.aiGLM-5.3-Flash (Z.ai docs)official · Retrieved 2026-11-13Vendor-reported value (self-reported by Z.ai). Value in the main text. Evaluation conditions are from the Footnotes of the HF card (zai-org/GLM-5.3-Flash, MIT) for the same announcement. Effort not stated (recommended setting: reasoning_effort: max). AutomationBench v1.0.6.transcribed from text
Source excerptGLM-5.3-Flash … 48.8 … on AutomationBenchLocation Text in the "Competitive Performance at Flash Cost" section of the docs.z.ai GLM-5.3-Flash page. Version: HF card Footnotes, AutomationBench (We evaluate on AutomationBench v1.0.6)

Related rankings

References