GLM-4.5: Specifications & Sources

Comparison cohort: vals-corp-fin-v2:2:overall
Metric: accuracy
Scale: 0-100
Participants: 75
Methodology and context: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-08-12. Latency in seconds: 95.244. Cost per task in USD: 0.03783. Source ID: vals-ai. Evidence capture ID: vals-corp_fin_v2-2026-09-29-83186cfafe52. Source payload hash: 83186cfafe526f0b8fe2ae86af05e8209fe799c8bfa48292ef1fef5db66650ee. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

TaxEval v2

Overall

1.Claude Sonnet 4.677.11%

2.Claude Fable 576.94%

3.GPT-5.6 Luna76.17%

3.GPT-5.6 Terra76.17%

5.Claude Fable 5.175.96%

6.Kimi K375.72%

7.Claude Opus 4.875.63%

7.Claude Sonnet 575.63%

9.GLM-5.3-Flash75.59%

10.Qwen 3.8 Max 090275.55%

11.Inkling Small75.51%

12.Inkling75.31%

12.Qwen 3.7 Max75.31%

14.Claude Opus 4.775.27%

15.GPT-5 mini75.23%

16.Claude Opus 575.14%

17.GPT-4.175.06%

18.GPT-5.574.98%

19.Gemini 3.6 Flash74.86%

20.o4-mini74.78%

21.GPT-5.6 Sol74.78%

22.Gemini 3.7 Flash74.73%

23.Kimi K2.674.65%

24.o374.57%

25.Gemini 3.8 Flash74.45%

26.Gemini 3.5 Flash74.37%

27.Claude Opus 4.574.33%

28.o174.28%

29.Kimi K2.574.2%

30.Grok 4.20 Reasoning74.12%

31.GPT-5.473.96%

32.Gemini 3 Flash Preview73.88%

33.MiMo-V2.5-Pro73.79%

34.GPT-573.39%

35.GLM-5.273.34%

36.Nemotron 3 Ultra73.1%

37.Mistral Large 373.06%

38.Gemini 3.1 Pro Preview72.88%

39.MiniMax M372.73%

40.Gemini 3.5 Flash-Lite72.61%

41.GLM-4.572.4%

42.GLM-5.372.36%

43.DeepSeek-R172.28%

44.DeepSeek-V4-Pro72.08%

45.GPT-4.1 mini71.91%

46.MiMo-V2.571.83%

47.Gemini 3.1 Flash-Lite71.79%

48.Kimi K2 Thinking71.71%

49.Grok 4.571.67%

50.GPT OSS 120B71.59%

51.Qwen 3.6 27B71.26%

52.GPT-5.4 mini71.22%

53.GLM-5.171.19%

54.DeepSeek-V3 032471.1%

54.Grok 4.671.1%

56.Qwen 3.8 27B70.85%

57.Grok 4.370.81%

58.Ling 3.0 Flash70.65%

59.Kimi K2 071170.2%

60.GLM-570.03%

61.o3-mini69.42%

62.GLM-4.768.77%

63.MiniMax M2.568.15%

64.Mistral Medium 3.567.99%

65.DeepSeek-V367.91%

66.GPT-5.4 nano67.42%

67.GPT-5 nano67.38%

68.MiniMax M2.766.56%

69.MiniMax M2.166.35%

70.GLM-4.666.24%

71.GPT OSS 20B63.7%

72.Command A61.37%

73.GPT-4.1 nano60.75%

74.GPT-4o mini60.55%

75.Mistral Small 3.158.3%

76.Llama 4 Scout55.19%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

|

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-tax-eval-v2:2:overall
Metric: accuracy
Scale: 0-100
Participants: 76
Methodology and context: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-09-01. Latency in seconds: 129.388. Cost per task in USD: 0.009559. Source ID: vals-ai. Evidence capture ID: vals-tax_eval_v2-2026-09-29-482e52f5e10e. Source payload hash: 482e52f5e10e64702bc003060f8c238a17c1d7d96a427fedf4f3297d5ba49963. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

GPQA Diamond

Overall

1.Gemini 3.1 Pro Preview95.45%

2.GPT-5.6 Sol95.2%

3.Grok 4.694.7%

4.Gemini 3.8 Flash94.44%

5.Gemini 3.7 Flash93.94%

6.Qwen 3.8 Max 090293.69%

7.Claude Fable 5.193.43%

7.Claude Opus 593.43%

7.Gemini 3.6 Flash93.43%

10.Claude Fable 593.18%

10.GPT-5.593.18%

12.Grok 4.592.93%

12.Kimi K392.93%

14.Gemini 3.5 Flash92.68%

14.MiniMax M392.68%

16.Claude Opus 4.892.42%

17.GPT-5.491.67%

17.GPT-5.6 Luna91.67%

19.Grok 4.391.41%

20.GPT-5.6 Terra90.91%

21.Claude Opus 4.790.15%

21.Qwen 3.7 Max90.15%

23.DeepSeek-V4-Pro89.39%

24.Kimi K2.689.14%

25.Claude Sonnet 588.89%

25.Qwen 3.8 27B88.89%

27.Grok 4.20 Reasoning88.64%

28.GLM-5.388.13%

29.Gemini 3 Flash Preview87.88%

30.Inkling87.12%

31.MiniMax M2.786.62%

32.GLM-5.3-Flash86.36%

33.Nemotron 3 Ultra86.11%

34.Claude Sonnet 4.685.61%

34.GLM-5.285.61%

34.GPT-585.61%

37.Ling 3.0 Flash84.85%

38.GLM-5.184.52%

39.Kimi K2.584.09%

39.o384.09%

41.Gemini 3.5 Flash-Lite83.84%

42.Inkling Small83.59%

43.GLM-583.33%

44.GPT-5.4 mini83.08%

45.MiMo-V2.5-Pro82.58%

46.MiniMax M2.582.07%

47.MiMo-V2.581.57%

48.Gemini 3.1 Flash-Lite81.06%

49.GPT-5 mini80.3%

50.GLM-4.780.05%

51.Claude Opus 4.579.55%

52.GPT OSS 120B78.54%

52.Kimi K2 Thinking78.54%

52.MiniMax M2.178.54%

55.GPT-5.4 nano77.53%

56.DeepSeek-V3.276.26%

57.o3-mini75.51%

58.GLM-4.674.5%

58.o4-mini74.5%

60.o173.23%

61.GLM-4.572.22%

62.Kimi K2 071171.46%

63.GPT OSS 20B68.94%

64.Mistral Large 368.43%

65.GPT-4.1 mini67.93%

66.GPT-4.165.4%

67.GPT-5 nano63.38%

68.DeepSeek-V3 032461.62%

69.DeepSeek-V354.55%

70.GPT-4.1 nano50.76%

71.Command A48.49%

72.Llama 4 Scout46.97%

73.GPT-4o mini44.19%

73.Mistral Small 3.144.19%

75.Mistral Medium 3.534.85%

76.Command R+31.06%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

|

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-gpqa:1:overall
Metric: accuracy
Scale: 0-100
Participants: 76
Methodology and context: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Latency in seconds: 704.224. Cost per task in USD: 0.019454. Source ID: vals-ai. Evidence capture ID: vals-gpqa-2026-09-29-8caf7b4807e8. Source payload hash: 8caf7b4807e87a2880c30218acea7855ea3a11721d56f7e049a77fadaf35dd34. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

LiveCodeBench v6

Overall

1.Claude Fable 5.190.52%

2.Claude Fable 589.78%

3.Gemini 3.8 Flash89.48%

4.Claude Opus 589.03%

5.Gemini 3.7 Flash88.65%

6.Gemini 3.1 Pro Preview88.49%

7.Grok 4.688.22%

8.Gemini 3.6 Flash88.08%

9.Qwen 3.8 Max 090287.85%

10.Claude Opus 4.887.82%

11.Gemini 3.5 Flash87.6%

12.DeepSeek-V4-Pro87.48%

13.Grok 4.587.35%

14.GPT-5.3-Codex87.31%

15.Kimi K387.19%

16.Qwen 3.7 Max87.06%

17.Kimi K2.686.77%

18.GPT-5 mini86.61%

19.Nemotron 3 Ultra85.98%

20.Inkling Small85.93%

21.GPT-5.6 Terra85.93%

22.GPT-585.91%

23.Gemini 3 Flash Preview85.59%

24.Inkling85.52%

25.GPT-5.585.3%

26.Claude Opus 4.785.07%

27.Grok 4.384.49%

28.Grok 4.20 Reasoning84.27%

29.GPT-5.484.14%

30.GPT-5.4 nano84.01%

31.Qwen 3.8 27B84%

32.Ling 3.0 Flash83.99%

33.o383.91%

34.Kimi K2.583.87%

35.GPT OSS 120B83.23%

36.GPT-5.6 Sol82.6%

37.Claude Sonnet 582.43%

38.GLM-4.782.23%

39.o4-mini82.21%

40.MiniMax M382.15%

41.Claude Sonnet 4.682.09%

42.Kimi K2.7 Code82.05%

43.GLM-581.87%

44.MiniMax M2.181.76%

45.MiMo-V2.581.51%

46.GPT-5.4 mini81.47%

47.GLM-5.181.38%

48.MiMo-V2.5-Pro81.35%

49.GLM-4.681.04%

50.GLM-5.380.54%

51.GLM-5.3-Flash80.51%

52.GPT OSS 20B80.39%

53.Gemini 3.1 Flash-Lite80.12%

54.MiniMax M2.779.93%

55.MiniMax M2.579.21%

56.Gemini 3.5 Flash-Lite79.01%

57.Claude Opus 4.575.03%

58.o3-mini71.48%

59.Kimi K2 071170.45%

60.DeepSeek-R170.22%

61.GPT-5 nano70.22%

62.DeepSeek-V3.269.86%

63.GLM-5.269.5%

64.GLM-4.567.45%

65.DeepSeek-V3 032465.48%

66.Kimi K2 Thinking63.15%

67.GPT-4.1 mini58.16%

68.Mistral Large 355.34%

69.GPT-4.154.67%

70.o150.26%

71.GPT-4o43.44%

72.GPT-4.1 nano42.72%

73.Llama 4 Scout38.54%

74.Command A35.07%

75.Mistral Small 3.131.82%

76.GPT-4o mini26.42%

77.Command R+18.24%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

|

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-lcb:1:overall
Metric: accuracy
Scale: 0-100
Participants: 77
Methodology and context: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Latency in seconds: 391.268. Cost per task in USD: 0.018278. Source ID: vals-ai. Evidence capture ID: vals-lcb-2026-09-29-b6ee1006a41a. Source payload hash: b6ee1006a41aab0c68eef9d3e42a2151634fffaaeb6bdc2230a6d02994198a59. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

LegalBench

Overall

1.Claude Fable 588.56%

2.Claude Fable 5.188.51%

3.Gemini 3.1 Pro Preview87.4%

4.Gemini 3.7 Flash87.26%

5.Gemini 3.8 Flash86.99%

6.Claude Opus 586.97%

7.GPT-5.6 Sol86.97%

8.Gemini 3 Flash Preview86.86%

9.Gemini 3.6 Flash86.71%

10.GPT-5.586.52%

11.Grok 4.686.31%

12.GPT-5.486.04%

13.GPT-586.02%

14.Kimi K386.02%

15.Grok 4.585.97%

16.MiniMax M385.42%

17.Claude Opus 4.785.25%

18.GPT-5.6 Terra85.11%

19.Qwen 3.7 Max84.91%

20.GLM-5.384.84%

21.Kimi K2.684.74%

22.Grok 4.384.46%

23.GLM-5.184.39%

24.Grok 4.784.39%

25.Gemini 3.5 Flash-Lite84.07%

25.GLM-5.284.07%

27.GLM-584.06%

28.GPT-5.6 Luna84.03%

29.MiniMax M2.783.98%

30.GLM-5.3-Flash83.93%

31.Claude Sonnet 583.92%

32.Gemini 3.1 Flash-Lite83.76%

33.o383.76%

34.Qwen 3.8 Max 090283.61%

35.Gemini 3.5 Flash83.6%

36.Claude Opus 4.883.57%

37.GLM-4.783.36%

38.DeepSeek-V4.1-Flash83.28%

39.GPT-4.183.1%

40.Mercury 2.583.06%

41.Inkling Small82.99%

42.Inkling82.95%

43.Claude Opus 4.582.84%

44.Qwen 3.8 27B82.43%

45.Claude Sonnet 4.682.12%

46.Nemotron 3 Ultra82.07%

47.GPT-5 mini81.77%

48.Kimi K2 071181.45%

49.DeepSeek-V380.76%

50.o180.39%

51.DeepSeek-V4-Pro80.32%

52.Kimi K2 Thinking80.2%

53.MiniMax M2.579.96%

54.Command A79.7%

55.Ling 3.0 Flash79.69%

56.GLM-4.679.61%

57.o4-mini79.19%

58.Mistral Large 379.14%

59.MiMo-V2.578.89%

60.GPT-4.1 mini78.04%

61.GPT-5.4 nano77.92%

62.Grok 4.20 Reasoning77.74%

63.DeepSeek-V3 032477.73%

64.MiMo-V2.5-Pro77.13%

65.GPT OSS 120B75.94%

66.GLM-4.575.63%

67.MiniMax M2.175.45%

68.Llama 4 Scout72.04%

69.o3-mini71.54%

70.GPT OSS 20B70.85%

71.Mistral Small 3.169.16%

72.Command R+68.29%

73.Gemma 2 27B67.98%

74.DeepSeek-R167.32%

75.DeepSeek-V3.265.96%

76.GPT-4.1 nano61.06%

77.GPT-5 nano50.13%

78.Command R32.97%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

|

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-legal-bench:1:overall
Metric: accuracy
Scale: 0-100
Participants: 78
Methodology and context: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-27. Latency in seconds: 16.402. Source ID: vals-ai. Evidence capture ID: vals-legal_bench-2026-09-29-c1213019b552. Source payload hash: c1213019b55234a262ae86fd4ebfe291530f315c988a4ee32fd501c13777f85f. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

Mathematics

MATH 500

Overall

1.GPT-596%

2.GPT OSS 120B94.8%

2.GPT-5 mini94.8%

4.o394.6%

5.GPT OSS 20B94.2%

5.Kimi K2 071194.2%

5.o4-mini94.2%

8.GLM-4.594%

9.GPT-5 nano93.8%

10.DeepSeek-R192.2%

11.o3-mini91.8%

12.o190.4%

13.MiniMax M2.189%

14.DeepSeek-V3 032488.6%

15.GPT-4.1 mini88%

16.GPT-4.187.2%

17.DeepSeek-V380.4%

18.GPT-4.1 nano80.2%

19.Llama 4 Scout79.2%

20.Command A76.2%

21.GPT-4o mini72.6%

22.Mistral Small 3.168.4%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

|

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-math500:1:overall
Metric: accuracy
Scale: 0-100
Participants: 22
Methodology and context: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-01-09. Latency in seconds: 84.928. Cost per task in USD: 0.012744. Source ID: vals-ai. Evidence capture ID: vals-math500-2026-09-29-62411eb86259. Source payload hash: 62411eb8625948521e074a88585b8309cfdb10b7ecf042ef7312373f008b6209. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

MGSM

Overall

1.Claude Opus 4.594.76%

2.o4-mini93.42%

3.Gemini 3 Flash Preview93.31%

4.GPT-592.84%

5.GPT-5 mini92.58%

6.DeepSeek-R192.25%

7.DeepSeek-V392.15%

8.GPT OSS 120B92.04%

9.o391.75%

10.DeepSeek-V3 032491.67%

11.o3-mini91.35%

12.Kimi K2 071190.95%

13.DeepSeek-V3.290.87%

14.GLM-4.590.84%

15.Kimi K2 Thinking90.15%

16.GLM-4.689.75%

17.GPT-5 nano89.31%

17.o189.31%

19.GPT OSS 20B89.02%

20.GLM-4.788.18%

21.Llama 4 Scout87.96%

22.MiniMax M2.187.85%

23.GPT-4.1 mini87.78%

24.GPT-4.187.67%

25.GPT-4o mini86.18%

26.Command A85.71%

27.Mistral Large 385.42%

28.Mistral Small 3.184.22%

29.GPT-4.1 nano69.27%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

|

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-mgsm:1:overall
Metric: accuracy
Scale: 0-100
Participants: 29
Methodology and context: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-01-09. Latency in seconds: 89.549. Cost per task in USD: 0.006319. Source ID: vals-ai. Evidence capture ID: vals-mgsm-2026-09-29-c67395c9276b. Source payload hash: c67395c9276b40cb0779a8c4ce4d254c7ab19874322f51486687c9e65f97e390. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

MedQA

Overall

1.o196.52%

2.Gemini 3.1 Pro Preview96.37%

3.GPT-596.32%

4.GPT-5.496.09%

5.GPT-5 mini96.06%

5.o396.06%

7.o4-mini96.02%

8.Gemini 3 Flash Preview95.81%

9.o3-mini94.83%

10.Grok 4.20 Reasoning94.55%

11.Kimi K2.594.37%

12.GLM-594.27%

13.GLM-4.793.74%

14.GPT-5 nano93.26%

15.Claude Opus 4.593.16%

16.Kimi K2 Thinking92.59%

17.MiniMax M2.592.53%

18.GLM-4.692.23%

19.Claude Sonnet 4.692.06%

20.GPT OSS 120B91.36%

21.GPT-4.191.18%

22.MiniMax M2.191.16%

23.DeepSeek-R190.8%

24.GLM-4.589.98%

25.DeepSeek-V3.289.45%

26.GPT-4o88.16%

27.GPT-4.1 mini84.63%

28.Kimi K2 071183.98%

29.GPT OSS 20B82.88%

30.Mistral Large 382.23%

31.DeepSeek-V3 032482%

32.DeepSeek-V380.9%

33.Command A80.55%

34.GPT-4o mini72.44%

35.Mistral Small 3.169.1%

36.GPT-4.1 nano68.23%

37.Mixtral 8x22B62.14%

38.Llama 4 Scout50.9%

39.Command R+2.65%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

|

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-medqa:1:overall
Metric: accuracy
Scale: 0-100
Participants: 39
Methodology and context: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-04-16. Latency in seconds: 59.609. Cost per task in USD: 0.003386. Source ID: vals-ai. Evidence capture ID: vals-medqa-2026-09-29-2886a92806d7. Source payload hash: 2886a92806d7b2e892c96203b7c7b462a4e28ec54dae900401734c38aa443883. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

MMLU-Pro

Overall

1.Claude Fable 5.192.38%

2.Claude Opus 591.59%

3.Claude Fable 591.5%

4.Gemini 3.1 Pro Preview90.99%

5.Gemini 3.8 Flash90.22%

6.Gemini 3.7 Flash90.12%

7.Claude Opus 4.789.87%

8.Claude Opus 4.889.59%

9.Gemini 3.5 Flash89.52%

10.Grok 4.689.4%

11.Qwen 3.7 Max89.31%

12.Gemini 3.6 Flash89.28%

13.Grok 4.589.22%

14.GPT-5.6 Sol89.1%

15.Qwen 3.8 Max 090288.6%

16.Gemini 3 Flash Preview88.59%

17.GPT-5.588.14%

18.Kimi K387.97%

19.Kimi K2.687.57%

20.Claude Sonnet 587.55%

21.GPT-5.487.48%

22.Claude Sonnet 4.687.34%

23.DeepSeek-V4-Pro87.25%

24.MiniMax M2.187.05%

25.GLM-5.186.9%

26.GLM-5.386.77%

27.GLM-5.286.71%

28.GPT-5.6 Terra86.66%

29.GPT-586.54%

30.Inkling86.3%

31.Grok 4.20 Reasoning86.25%

32.Gemini 3.1 Flash-Lite86.24%

33.GLM-5.3-Flash86.06%

34.GPT-5.6 Luna86.04%

35.GLM-586.03%

36.Kimi K2.585.91%

37.Grok 4.385.84%

38.Gemini 3.5 Flash-Lite85.84%

39.Nemotron 3 Ultra85.76%

40.o385.6%

41.Claude Opus 4.585.59%

42.Inkling Small85.57%

43.MiMo-V2.5-Pro84.6%

44.GPT-5.4 mini84.55%

45.Qwen 3.8 27B84.34%

46.MiniMax M384.22%

47.o183.49%

48.DeepSeek-R183.18%

49.DeepSeek-V3.283.06%

50.MiMo-V2.582.93%

51.GLM-4.782.74%

52.GPT-5 mini82.23%

53.GLM-4.682.2%

54.Ling 3.0 Flash82.01%

55.GLM-4.581.22%

56.Kimi K2 Thinking81.07%

57.o4-mini80.56%

58.GPT-4.180.5%

59.MiniMax M2.780.43%

60.MiniMax M2.580.09%

61.Mistral Large 379.82%

62.DeepSeek-V3 032479.47%

63.Kimi K2 071179.39%

64.GPT OSS 120B79.17%

65.o3-mini78.69%

66.GPT-4.1 mini77.23%

67.GPT-5.4 nano77.17%

68.GPT-5 nano76.07%

69.Mistral Medium 3.575.34%

70.DeepSeek-V373.82%

71.GPT OSS 20B71.64%

72.Llama 4 Scout69.63%

73.Command A69.17%

74.Mistral Small 3.166.02%

75.GPT-4.1 nano63.48%

76.GPT-4o mini62.74%

77.Command R+44%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

|

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-mmlu-pro:1:overall
Metric: accuracy
Scale: 0-100
Participants: 77
Methodology and context: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Latency in seconds: 136.72. Cost per task in USD: 0.009757. Source ID: vals-ai. Evidence capture ID: vals-mmlu_pro-2026-09-29-383f4d5d1419. Source payload hash: 383f4d5d141971e7bb60b6c77a0df7a2be27ee6a005dd8854eb2df953dec36a4. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

AIME: Overall (Show measurement, test conditions, and source)

Source value: 86.667
Score: 86.667
Metric: accuracy
Unit: %
Benchmark version: 1
Category: math
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-aime:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-04-16. Latency in seconds: 333.117. Cost per task in USD: 0.04689. Source ID: vals-ai. Evidence capture ID: vals-aime-2026-09-29-227b72e1c9a4. Source payload hash: 227b72e1c9a4fe760e2c88a32596a26a75b3881bf338eac9fa92f76b52b2f3e5. Parser version: vals-astro-v2. Imported at: 2026-09-29
Context: The source dataset marks this benchmark as archived. The result remains visible as historical evidence and is not interchangeable with an active leaderboard.

Source Vals AI

GLM-4.5 aggregate score (Show measurement, test conditions, and source)

Source value: 63.2
Score: 63.2
Metric: points
Unit: points
Category: composite
Direction: Higher is better
Source type: vendor-reported
Evaluator: GLM-4.5 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. 12-industry-benchmark composite; exact benchmark weighting not exposed

Source GLM-4.5 model card

Recorded measurement details

CorpFin v2: Overall (Show measurement, test conditions, and source)

Source value: 60.956
Score: 60.956
Metric: accuracy
Unit: %
Benchmark version: 2
Category: finance
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-corp-fin-v2:2:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-08-12. Latency in seconds: 95.244. Cost per task in USD: 0.03783. Source ID: vals-ai. Evidence capture ID: vals-corp_fin_v2-2026-09-29-83186cfafe52. Source payload hash: 83186cfafe526f0b8fe2ae86af05e8209fe799c8bfa48292ef1fef5db66650ee. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

GPQA Diamond: Overall (Show measurement, test conditions, and source)

Source value: 72.222
Score: 72.222
Metric: accuracy
Unit: %
Benchmark version: 1
Category: reasoning
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-gpqa:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Latency in seconds: 704.224. Cost per task in USD: 0.019454. Source ID: vals-ai. Evidence capture ID: vals-gpqa-2026-09-29-8caf7b4807e8. Source payload hash: 8caf7b4807e87a2880c30218acea7855ea3a11721d56f7e049a77fadaf35dd34. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

LiveCodeBench v6: Overall (Show measurement, test conditions, and source)

Source value: 67.446
Score: 67.446
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-lcb:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Latency in seconds: 391.268. Cost per task in USD: 0.018278. Source ID: vals-ai. Evidence capture ID: vals-lcb-2026-09-29-b6ee1006a41a. Source payload hash: b6ee1006a41aab0c68eef9d3e42a2151634fffaaeb6bdc2230a6d02994198a59. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

LegalBench: Overall (Show measurement, test conditions, and source)

Source value: 75.627
Score: 75.627
Metric: accuracy
Unit: %
Benchmark version: 1
Category: legal
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-legal-bench:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-27. Latency in seconds: 16.402. Source ID: vals-ai. Evidence capture ID: vals-legal_bench-2026-09-29-c1213019b552. Source payload hash: c1213019b55234a262ae86fd4ebfe291530f315c988a4ee32fd501c13777f85f. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

MATH 500: Overall (Show measurement, test conditions, and source)

Source value: 94
Score: 94
Metric: accuracy
Unit: %
Benchmark version: 1
Category: math
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-math500:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-01-09. Latency in seconds: 84.928. Cost per task in USD: 0.012744. Source ID: vals-ai. Evidence capture ID: vals-math500-2026-09-29-62411eb86259. Source payload hash: 62411eb8625948521e074a88585b8309cfdb10b7ecf042ef7312373f008b6209. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

MedQA: Overall (Show measurement, test conditions, and source)

Source value: 89.975
Score: 89.975
Metric: accuracy
Unit: %
Benchmark version: 1
Category: health
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-medqa:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-04-16. Latency in seconds: 59.609. Cost per task in USD: 0.003386. Source ID: vals-ai. Evidence capture ID: vals-medqa-2026-09-29-2886a92806d7. Source payload hash: 2886a92806d7b2e892c96203b7c7b462a4e28ec54dae900401734c38aa443883. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

MGSM: Overall (Show measurement, test conditions, and source)

Source value: 90.836
Score: 90.836
Metric: accuracy
Unit: %
Benchmark version: 1
Category: math
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-mgsm:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-01-09. Latency in seconds: 89.549. Cost per task in USD: 0.006319. Source ID: vals-ai. Evidence capture ID: vals-mgsm-2026-09-29-c67395c9276b. Source payload hash: c67395c9276b40cb0779a8c4ce4d254c7ab19874322f51486687c9e65f97e390. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

MMLU-Pro: Overall (Show measurement, test conditions, and source)

Source value: 81.222
Score: 81.222
Metric: accuracy
Unit: %
Benchmark version: 1
Category: knowledge
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-mmlu-pro:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Latency in seconds: 136.72. Cost per task in USD: 0.009757. Source ID: vals-ai. Evidence capture ID: vals-mmlu_pro-2026-09-29-383f4d5d1419. Source payload hash: 383f4d5d141971e7bb60b6c77a0df7a2be27ee6a005dd8854eb2df953dec36a4. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

TaxEval v2: Overall (Show measurement, test conditions, and source)

Source value: 72.404
Score: 72.404
Metric: accuracy
Unit: %
Benchmark version: 2
Category: finance
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-tax-eval-v2:2:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: zai/glm-4.5. Source model name: GLM-4.5. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-09-01. Latency in seconds: 129.388. Cost per task in USD: 0.009559. Source ID: vals-ai. Evidence capture ID: vals-tax_eval_v2-2026-09-29-482e52f5e10e. Source payload hash: 482e52f5e10e64702bc003060f8c238a17c1d7d96a427fedf4f3297d5ba49963. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

Our tests

Each test shows the latest attempt, with no subsequent fixes to the generated code. Earlier runs remain available in the test details. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

GLM-4.5

Output withheld for safety

Reasoning (requested): high

Current attempt

Run date: 2 Oct 2026
API provider: openrouter
Requested API model: z-ai/glm-4.5
API model reported in response: z-ai/glm-4.5
Reasoning setting: high
Pinned endpoint: Z.AI | z-ai/glm-4.5
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 164.5 s

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Earlier attempts (1)

1 Oct 2026Output withheld for safetyReasoning setting: high

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

Popularity

39.8 / 100

Specifications and access

Specification	Value and source
Weights	Open weightsSource
Access	API, LocalSource
Parameters	355BSource
Active parameters	32BSource
Context window	131,072 tokensSource
License	MITSource
Architecture	MoE hybrid reasoning modelSource
Parameters	355 BSource
Active parameters	32 BSource
Input	TextSource
Output	TextSource
Reasoning mode	thinking, non-thinkingSource
Tool calling	YesSource
API model ID	glm-4.5Source

Published prices

Hosting-market price: the median of 1 OpenRouter endpoints from 1 providers (representative: Z.AI), observed on October 7, 2026. Cache prices differ by provider and are not shown.

API input: $0.6 per 1M tokensSource
API output: $2.2 per 1M tokensSource

Predecessor and successor

Sources and data date

Type	Evidence and data date
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · GLM-4.5 model card (retrieved September 8, 2026) · GLM-4.5 model card text · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · GLM-4.5 model card (retrieved September 8, 2026) · GLM-4.5 model card text · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Unresolved	detailed-benchmarks Original wording Card says 12 benchmark evaluation but exposes only an aggregate score; benchmark graphic/table was not available in the checked raw card.
Unresolved	release-date Original wording No normalized release-date field.
Unresolved	AA benchmark rows Original wording No exact Artificial Analysis model page located in the checked public sitemap.
Additional source	Model metadata · GLM-4.5 model card · Editorial description reviewed October 2, 2026
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Model metadata (retrieved September 8, 2026) · GLM-4.5 documentation · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0
Additional source	Z.ai Developer Docs, GLM-4.6 overview (2026-09-19)