Context-Bench measures an agent's ability to perform context engineering with:

Filesystem Suite: Evaluates how well language models can chain file operations, trace entity relationships, and manage multi-step information retrieval.
Skills Suite: Evalutes how well language models can discover and load relevant skills from a library to complete tasks.

Last updated: Dec 18, 2025

Interested in contributing a task or model? Email us or open an issue on GitHub.

#

Model

Filesystem Rubric

1

openai/gpt-5.2-2025-12-11 (xhigh)

82.61%$84.66

2

openai/gpt-5.2-2025-12-11 (high)

80.5%$68.53

3

anthropic/claude-opus-4-5-20251101

76.8%$39.91

4

openai/gpt-5.1-2025-11-13

76.59%$47.22

5

openai/gpt-5.1-codex

76.17%$63.99

6

google/gemini-3-pro-preview

75.33%$95.87

7

anthropic/claude-sonnet-4-5-20250929

74%$24.58

8

openai/gpt-5.2-2025-12-11 (medium)

73.32%$60.34

9

deepseek/deepseek-reasoner

73.05%$16.03

10

openai/gpt-5-2025-08-07

72.67%$43.56

11

openai/gpt-5.1-codex-mini

70.83%$14.05

12

google/gemini-3-flash-preview

68.17%$36.74

13

openai/gpt-5-mini-2025-08-07

64.33%$12.45

14

deepseek/deepseek-chat

63.35%$13.05

15

anthropic/claude-haiku-4-5-20251001

61.02%$10.18

16

anthropic/claude-opus-4-1-20250805

61%$110.89

17

z-ai/glm-4.6

56.83%$21.32

18

minimax/minimax-m2

56.83%$5.21

19

moonshotai/kimi-k2-0905

55.13%$12.08

20

moonshotai/kimi-k2-thinking

55%$21.83

21

openai/gpt-5-nano-2025-08-07

44.83%$2.43

22

openai/gpt-4.1-2025-04-14

36.68%$36.85

23

openai/gpt-4.1-mini-2025-04-14

36.3%$13.56

24

mistralai/mistral-large-2512

23.8%$8.97

25

openai/gpt-oss-120b

20.2%$2.19

26

openai/gpt-4.1-nano-2025-04-14

16.2%$0.98

27

deepseek/deepseek-chat-v3.1

11.97%$2.54

28

openai/gpt-oss-20b

6.67%$0.54

#

Model

Task Completion Rubric

Skill Use Rubric

1

openai/gpt-5.2-2025-12-11 (xhigh)

85.31%

63.12%

2

openai/gpt-5.2-2025-12-11 (high)

84.47%

54.21%

3

openai/gpt-5.2-2025-12-11 (medium)

77.55%

49.74%

4

anthropic/claude-sonnet-4-5-20250929

76.5%

72%

5

anthropic/claude-opus-4-5-20251101

75.54%

68.82%

6

deepseek/deepseek-chat

75.33%

53.62%

7

anthropic/claude-opus-4-1-20250805

74.4%

71.8%

8

google/gemini-3-pro

72.73%

64.29%

9

deepseek/deepseek-reasoner

70.48%

56.12%

10

openai/gpt-5-2025-08-07

70.2%

51.4%

11

anthropic/claude-haiku-4-5-20251001

69.7%

57.3%

12

openai/gpt-5-mini-2025-08-07

68.8%

45.5%

13

z-ai/glm-4.6

65.9%

50%

14

openai/gpt-5.1-codex

64.84%

55.73%

15

openai/gpt-5.1

63.75%

55.75%

16

google/gemini-3-flash

59.54%

59.54%

17

mistralai/mistral-large-3

56.25%

36.93%

18

openai/gpt-5-nano-2025-08-07

52.8%

24%

19

openai/gpt-5.1-codex-mini

49.72%

23.58%

20

openai/gpt-4.1-2025-04-14

36.1%

31.3%

Leaderboard Updates

December 18, 2025

Gemini 3 Flash
- Outperforms Haiku and GPT 5 Mini on Filesystem
- Less token efficient, leading to higher costs

December 11, 2025

GPT 5.2 (medium, high, xhigh)
- #1 on Filesystem (6% ↑) and Skills (9% ↑)
- 1.5-2.1x Opus cost but still cheaper than Gemini 3 Pro

December 9, 2025

Deepseek v3.2 (reasoner, chat)
- #1 OSS and only 1% behind Sonnet 4.5
- 16% ↑ on Filesystem and 10% ↑ on Skills over GLM 4.6
Mistral Large 3
- Ranks below GPT 4.1 Mini on Filesystem

November 26, 2025

GPT 5.1, 5.1 Codex, 5.1 Codex Mini
Gemini 3 Pro
Claude Opus 4.5

November 7, 2025

Launched Skills Suite
Kimi K2 Thinking

November 4, 2025

Minimax M2

October 28, 2025

Launched leaderboard website
Launched Filesystem Suite