Context Arena

Long-context benchmark leaderboard for multi-needle retrieval and reasoning across increasing context lengths, reported as GDM-MRCRv2 scores.

70rows
avg_score_overallprimary metric
2026-05-06sampled

Metadata

Metrics

Average Score, AUC 128K, AUC 1M, Cumulative Average 128K, Cumulative Average 1M, Average Token Efficiency, Total Runs

Latest Results

Rows ranked by average score over all available context bins. Ratio metrics are converted to percentages.

Rank Subject Average Score Model Match Provenance Sampled
1 openai/gpt-5.5 79.77 GPT-5.5
openai-gpt-5.5
Imported 2026-05-06
2 openai/gpt-5.5 78.96 GPT-5.5
openai-gpt-5.5
Imported 2026-05-06
3 openai/gpt-5.5 78.59 GPT-5.5
openai-gpt-5.5
Imported 2026-05-06
4 openai/gpt-5.5 75.03 GPT-5.5
openai-gpt-5.5
Imported 2026-05-06
5 anthropic/claude-opus-4.6 73.06 Claude Opus 4.6
anthropic-claude-opus-4.6
Imported 2026-05-06
6 anthropic/claude-opus-4.6 72.43 Claude Opus 4.6
anthropic-claude-opus-4.6
Imported 2026-05-06
7 anthropic/claude-opus-4.6 72.26 Claude Opus 4.6
anthropic-claude-opus-4.6
Imported 2026-05-06
8 anthropic/claude-sonnet-4.6 70.50 Claude Sonnet 4.6
anthropic-claude-sonnet-4.6
Imported 2026-05-06
9 anthropic/claude-sonnet-4.6 70.38 Claude Sonnet 4.6
anthropic-claude-sonnet-4.6
Imported 2026-05-06
10 anthropic/claude-sonnet-4.6 69.61 Claude Sonnet 4.6
anthropic-claude-sonnet-4.6
Imported 2026-05-06
11 openai/gpt-5.4 67.65 GPT-5.4
openai-gpt-5.4
Imported 2026-05-06
12 openai/gpt-5.4 66.15 GPT-5.4
openai-gpt-5.4
Imported 2026-05-06
13 moonshotai/kimi-k2.6 64.63 KIMI MoonshotAI: Kimi K2.6
moonshotai-kimi-k2.6
Imported 2026-05-06
14 openai/gpt-5.4 62.89 GPT-5.4
openai-gpt-5.4
Imported 2026-05-06
15 z-ai/glm-5.1 62.05 GLM GLM 5.1
z-ai-glm-5.1
Imported 2026-05-06
16 openai/gpt-5.4 59.32 GPT-5.4
openai-gpt-5.4
Imported 2026-05-06
17 moonshotai/kimi-k2.5 59.22 KIMI MoonshotAI: Kimi K2.5
moonshotai-kimi-k2.5
Imported 2026-05-06
18 deepseek/deepseek-v4-pro 55.99 DeepSeek V4 Pro
deepseek-deepseek-v4-pro
Imported 2026-05-06
19 google/gemini-3.1-pro-preview 53.84 Gemini 3.1 Pro Preview
google-gemini-3.1-pro-preview
Imported 2026-05-06
20 moonshotai/kimi-k2.5 53.33 KIMI MoonshotAI: Kimi K2.5
moonshotai-kimi-k2.5
Imported 2026-05-06
21 moonshotai/kimi-k2.6 51.88 KIMI MoonshotAI: Kimi K2.6
moonshotai-kimi-k2.6
Imported 2026-05-06
22 deepseek/deepseek-v4-flash 50.93 DeepSeek V4 Flash
deepseek-deepseek-v4-flash
Imported 2026-05-06
23 nvidia/nemotron-3-super-120b-a12b 50.29 Nemotron 3 Super
nvidia-nemotron-3-super-120b-a12b
Imported 2026-05-06
24 openai/gpt-5.4-nano 48.78 GPT-5.4 Nano
openai-gpt-5.4-nano
Imported 2026-05-06
25 google/gemini-3.1-pro-preview 48.69 Gemini 3.1 Pro Preview
google-gemini-3.1-pro-preview
Imported 2026-05-06
26 anthropic/claude-opus-4.6 48.19 Claude Opus 4.6
anthropic-claude-opus-4.6
Imported 2026-05-06
27 google/gemini-3-flash-preview 46.79 Gemini 3 Flash Preview
google-gemini-3-flash-preview
Imported 2026-05-06
28 anthropic/claude-sonnet-4.6 46.73 Claude Sonnet 4.6
anthropic-claude-sonnet-4.6
Imported 2026-05-06
29 google/gemini-3-flash-preview 46.24 Gemini 3 Flash Preview
google-gemini-3-flash-preview
Imported 2026-05-06
30 openai/gpt-5.4-mini 45.67 GPT-5.4 Mini
openai-gpt-5.4-mini
Imported 2026-05-06
31 openai/gpt-5.4-mini 44.79 GPT-5.4 Mini
openai-gpt-5.4-mini
Imported 2026-05-06
32 openai/gpt-5.4-mini 42.08 GPT-5.4 Mini
openai-gpt-5.4-mini
Imported 2026-05-06
33 google/gemini-3-flash-preview 39.58 Gemini 3 Flash Preview
google-gemini-3-flash-preview
Imported 2026-05-06
34 xiaomi/mimo-v2-omni 37.85 MiMo-V2-Omni
xiaomi-mimo-v2-omni
Imported 2026-05-06
35 anthropic/claude-haiku-4.5 36.27 Claude Haiku 4.5
anthropic-claude-haiku-4.5
Imported 2026-05-06
36 xiaomi/mimo-v2.5-pro 36.22 MiMo-V2.5-Pro
xiaomi-mimo-v2.5-pro
Imported 2026-05-06
37 openai/gpt-5.4-nano 36.17 GPT-5.4 Nano
openai-gpt-5.4-nano
Imported 2026-05-06
38 google/gemini-3.1-flash-lite-preview 34.90 Gemini 3.1 Flash Lite Preview
google-gemini-3.1-flash-lite-preview
Imported 2026-05-06
39 openai/gpt-5.5 34.90 GPT-5.5
openai-gpt-5.5
Imported 2026-05-06
40 openai/gpt-5.4-mini 34.47 GPT-5.4 Mini
openai-gpt-5.4-mini
Imported 2026-05-06
41 minimax/minimax-m2.7 33.29 MiniMax M2.7
minimax-minimax-m2.7
Imported 2026-05-06
42 google/gemini-3.1-flash-lite-preview 31.82 Gemini 3.1 Flash Lite Preview
google-gemini-3.1-flash-lite-preview
Imported 2026-05-06
43 xiaomi/mimo-v2.5 31.55 MiMo-V2.5
xiaomi-mimo-v2.5
Imported 2026-05-06
44 z-ai/glm-5.1 30.29 GLM GLM 5.1
z-ai-glm-5.1
Imported 2026-05-06
45 xiaomi/mimo-v2-pro 29.99 MiMo-V2-Pro
xiaomi-mimo-v2-pro
Imported 2026-05-06
46 openai/gpt-5.4-nano 29.90 GPT-5.4 Nano
openai-gpt-5.4-nano
Imported 2026-05-06
47 nvidia/nemotron-3-super-120b-a12b 29.30 Nemotron 3 Super
nvidia-nemotron-3-super-120b-a12b
Imported 2026-05-06
48 anthropic/claude-opus-4.7 28.81 Claude Opus 4.7
anthropic-claude-opus-4.7
Imported 2026-05-06
49 x-ai/grok-4.20 28.75 GROK Grok 4.20
x-ai-grok-4.20
Imported 2026-05-06
50 anthropic/claude-opus-4.7 28.63 Claude Opus 4.7
anthropic-claude-opus-4.7
Imported 2026-05-06
51 anthropic/claude-opus-4.7 28.54 Claude Opus 4.7
anthropic-claude-opus-4.7
Imported 2026-05-06
52 anthropic/claude-opus-4.7 27.96 Claude Opus 4.7
anthropic-claude-opus-4.7
Imported 2026-05-06
53 google/gemini-3.1-flash-lite-preview 26.94 Gemini 3.1 Flash Lite Preview
google-gemini-3.1-flash-lite-preview
Imported 2026-05-06
54 openai/gpt-5.4 26.69 GPT-5.4
openai-gpt-5.4
Imported 2026-05-06
55 deepseek/deepseek-v4-pro 26.31 DeepSeek V4 Pro
deepseek-deepseek-v4-pro
Imported 2026-05-06
56 google/gemini-3-flash-preview 25.60 Gemini 3 Flash Preview
google-gemini-3-flash-preview
Imported 2026-05-06
57 mistralai/mistral-small-4 25.35 Imported 2026-05-06
58 xiaomi/mimo-v2.5-pro 24.25 MiMo-V2.5-Pro
xiaomi-mimo-v2.5-pro
Imported 2026-05-06
59 xiaomi/mimo-v2.5 23.99 MiMo-V2.5
xiaomi-mimo-v2.5
Imported 2026-05-06
60 deepseek/deepseek-v4-flash 23.47 DeepSeek V4 Flash
deepseek-deepseek-v4-flash
Imported 2026-05-06
61 xiaomi/mimo-v2-pro 22.79 MiMo-V2-Pro
xiaomi-mimo-v2-pro
Imported 2026-05-06
62 openai/gpt-5.4-nano 21.87 GPT-5.4 Nano
openai-gpt-5.4-nano
Imported 2026-05-06
63 openai/gpt-5.4-mini 20.83 GPT-5.4 Mini
openai-gpt-5.4-mini
Imported 2026-05-06
64 xiaomi/mimo-v2-omni 20.56 MiMo-V2-Omni
xiaomi-mimo-v2-omni
Imported 2026-05-06
65 google/gemini-3.1-flash-lite-preview 18.23 Gemini 3.1 Flash Lite Preview
google-gemini-3.1-flash-lite-preview
Imported 2026-05-06
66 anthropic/claude-haiku-4.5 17.68 Claude Haiku 4.5
anthropic-claude-haiku-4.5
Imported 2026-05-06
67 anthropic/claude-opus-4.7 15.12 Claude Opus 4.7
anthropic-claude-opus-4.7
Imported 2026-05-06
68 x-ai/grok-4.20 14.49 GROK Grok 4.20
x-ai-grok-4.20
Imported 2026-05-06
69 mistralai/mistral-small-4 13.96 Imported 2026-05-06
70 openai/gpt-5.4-nano 12.31 GPT-5.4 Nano
openai-gpt-5.4-nano
Imported 2026-05-06