llmrun
Reasoning

SimpleBench Leaderboard

SimpleBench is a set of everyday, common-sense and trick questions that humans answer easily but language models often get wrong. It probes basic reasoning and robustness rather than specialist knowledge.

Source: epoch19 open models ranked+71 proprietaryData through Jul 2026

Open modelsAll models

All models ranked on SimpleBench

Proprietary / closed models are shown dimmed — you can't run them locally, but they show where the open field stands.

#ModelScore
1Claude Fable 5 Max · proprietary
81.9%
2Gemini 3.1 Pro Preview · proprietary
79.6%
3GPT 5.5 Pro (high) · proprietary
76.9%
4GPT 5.5 Pro (unspecified) · proprietary
76.9%
5Gemini 3.5 Flash (unspecified) · proprietary
76.7%
6Gemini 3 Pro Preview · proprietary
76.4%
7GPT 5.4 Pro (Mar 05, 2026, unspecified) · proprietary
74.1%
8GPT 5.6 Sol Prounknown · proprietary
71.7%
9Qwen3.7 Max · proprietary
70.4%
10Grok 4.5 (unspecified) · proprietary
70.0%
11GPT 5.5 (unspecified) · proprietary
69.0%
12Claude Opus 4.6 · proprietary
67.6%
13Claude Opus 4.8 (unspecified) · proprietary
64.8%
14GPT 5.6 Sol (unspecified) · proprietary
64.8%
15Qwen3.6 Max Preview · proprietary
63.0%
16Claude Opus 4.7 (unspecified) · proprietary
62.9%
17Gemini 2.5 Pro Preview (Jun 05) · proprietary
62.4%
18Claude Opus 4.5 (Nov 01, 2025, unspecified) · proprietary
62.0%
19Claude Opus 4.5 (Nov 01, 2025) · proprietary
62.0%
20GPT 5 Pro (Oct 06, 2025, high) · proprietary
61.6%
21GPT 5 Pro (Oct 06, 2025, unspecified) · proprietary
61.6%
22DeepSeek V4 Pro · 861.6B
61.2%
23Gemini 3 Flash Preview · proprietary
61.1%
24Claude Sonnet 5 (unspecified) · proprietary
60.6%
25Grok 4 (Jul 09) · proprietary
60.5%
26Claude Opus 4.1 (Aug 05, 2025, unspecified) · proprietary
60.0%
27Claude Opus 4.1 (Aug 05, 2025) · proprietary
60.0%
28Claude Opus 4 (May 14, 2025, 12K) · proprietary
58.8%
29Claude Opus 4 (May 14, 2025, unspecified) · proprietary
58.8%
30Kimi K2.7 Code · 1058.6B
57.9%
31GPT 5.2 Pro (Dec 11, 2025) · proprietary
57.4%
32GPT 5 (Aug 07, 2025, high) · proprietary
56.7%
33Grok 4.1 Fast Non Reasoning · proprietary
56.0%
34Grok 4.1 Fast Reasoning · proprietary
56.0%
35GLM 5.1 · 753.9B
55.1%
36Claude Sonnet 4.5 (Sep 29, 2025, 12K) · proprietary
54.3%
37Claude Sonnet 4.5 (Sep 29, 2025, unspecified) · proprietary
54.3%
38GLM 5 · 753.9B
53.2%
39GPT 5.1 (Nov 13, 2025, high) · proprietary
53.2%
40O3 (Apr 16, 2025, high) · proprietary
53.1%
41DeepSeek V3.2 Speciale · 685.4B
52.6%
42Gemini 2.5 Pro Exp (Mar 25) · proprietary
51.6%
43Gemini 2.5 Pro Preview (Mar 25) · proprietary
51.6%
44GPT 5.6 Terra (unspecified) · proprietary
48.9%
45GLM 4.7 · 358.3B
47.7%
46GPT 5.6 Luna (unspecified) · proprietary
46.8%
47Kimi K2.5 · 1058.6B
46.8%
48Claude 3.7 Sonnet (Feb 19, 2025, 12K) · proprietary
46.4%
49Claude 3.7 Sonnet (Feb 19, 2025, unspecified) · proprietary
46.4%
50GPT 5.2 (Dec 11, 2025, high) · proprietary
45.8%
51GPT 5.2 (Dec 11, 2025, unspecified) · proprietary
45.8%
52MiniMax M3 · 427.0B
45.8%
53Claude Sonnet 4 (May 14, 2025, 12K) · proprietary
45.5%
54Claude Sonnet 4 (May 14, 2025, unspecified) · proprietary
45.5%
55Claude 3.7 Sonnet (Feb 19, 2025) · proprietary
44.9%
56O1 Preview (Sep 12, 2024) · proprietary
41.7%
57Claude 3.5 Sonnet (Oct 22, 2024) · proprietary
41.4%
58Gemini 2.5 Flash · proprietary
41.2%
59DeepSeek R1 0528 · 684.5B
40.8%
60O1 (Dec 17, 2024, high) · proprietary
40.1%
61DeepSeek V3.1 · 684.5B
40.0%
62O4 Mini (Apr 16, 2025, high) · proprietary
38.7%
63O1 (Dec 17, 2024, medium) · proprietary
36.7%
64Grok 3 · proprietary
36.1%
65Qwen3.6 Flash · proprietary
35.2%
66GPT 4.5 Preview (Feb 27, 2025) · proprietary
34.5%
67Gemini Exp (Dec 06) · proprietary
31.1%
68Qwen3 235B A22B · 235.1B
31.0%
69DeepSeek R1 · 684.5B
30.9%
70Gemini 2.0 Flash Thinking Exp (Jan 21) · proprietary
30.7%
71Llama 4 Maverick 17B 128E Instruct · 401.6B
27.7%
72Claude 3.5 Sonnet (Jun 20, 2024) · proprietary
27.5%
73DeepSeek v3 0324 · 684.5B
27.2%
74Gemini 1.5 Pro 002 · proprietary
27.1%
75GPT 4.1 (Apr 14, 2025) · proprietary
27.0%
76Kimi K2 Instruct · 1026.5B
26.3%
77GPT 4 Turbo (Apr 09, 2024) · proprietary
25.1%
78Claude 3 Opus (Feb 29, 2024) · proprietary
23.5%
79Llama 3.1 405B Instruct · 405.9B
23.0%
80O3 Mini (Jan 31, 2025, high) · proprietary
22.8%
81Grok 2 (Dec 12) · proprietary
22.7%
82Mistral Large 2407 · proprietary
22.5%
83GPT OSS 120B · 120.4B
22.1%
84Llama 3.3 70B Instruct · 70.6B
19.9%
85DeepSeek v3 · 684.5B
18.9%
86Gemini 2.0 Flash Exp · proprietary
18.9%
87O1 Mini (Sep 12, 2024, medium) · proprietary
18.1%
88GPT 4o (Aug 06, 2024) · proprietary
17.8%
89C4ai Command R Plus (Aug 2024) · proprietary
17.4%
90GPT 4o Mini (Jul 18, 2024) · proprietary
10.7%

Score vs model size

Which models give the most quality for their size — the ones worth running locally.

100B1Tmodel size (log scale) →61.2%18.9%Kimi K2.7 Code · 1.1T · 57.9%GLM 5 · 754B · 53.2%Kimi K2.5 · 1.1T · 46.8%MiniMax M3 · 427B · 45.8%DeepSeek R1 0528 · 685B · 40.8%DeepSeek V3.1 · 685B · 40.0%DeepSeek R1 · 685B · 30.9%Llama 4 Maverick 17B 128E Instruct · 402B · 27.7%DeepSeek v3 0324 · 685B · 27.2%Kimi K2 Instruct · 1T · 26.3%Llama 3.1 405B Instruct · 406B · 23.0%DeepSeek v3 · 685B · 18.9%Llama 3.3 70B Instruct · 71B · 19.9%Llama 3.3 70B InstructGPT OSS 120B · 120B · 22.1%GPT OSS 120BQwen3 235B A22B · 235B · 31.0%Qwen3 235B A22BGLM 4.7 · 358B · 47.7%GLM 4.7DeepSeek V3.2 Speciale · 685B · 52.6%DeepSeek V3.2 SpecialeGLM 5.1 · 754B · 55.1%GLM 5.1DeepSeek V4 Pro · 862B · 61.2%DeepSeek V4 Pro
Each dot is a model. Up = higher score, left = smaller (easier to run locally). The dashed line marks the efficiency frontier — the best score you can get at each size or smaller.
  • Llama 3.3 70B Instruct, 71B, score 19.9% — on the efficiency frontier (best score at its size or smaller).
  • GPT OSS 120B, 120B, score 22.1% — on the efficiency frontier (best score at its size or smaller).
  • Qwen3 235B A22B, 235B, score 31.0% — on the efficiency frontier (best score at its size or smaller).
  • GLM 4.7, 358B, score 47.7% — on the efficiency frontier (best score at its size or smaller).
  • DeepSeek V3.2 Speciale, 685B, score 52.6% — on the efficiency frontier (best score at its size or smaller).
  • GLM 5.1, 754B, score 55.1% — on the efficiency frontier (best score at its size or smaller).
  • DeepSeek V4 Pro, 862B, score 61.2% — on the efficiency frontier (best score at its size or smaller).

SimpleBench: frequently asked questions

What is the best open LLM on SimpleBench?
DeepSeek V4 Pro is the top open model on SimpleBench, scoring 61.2%. Among all models tested — including proprietary ones — it ranks #22. The top model overall is Claude Fable 5 Max (Anthropic) at 81.9%.
Can open models match proprietary models on SimpleBench?
Not quite on SimpleBench: the strongest proprietary model (Claude Fable 5 Max) scores 81.9%, ahead of the best open model (DeepSeek V4 Pro) at 61.2% — but you can run the open one yourself.

Scores aggregated from epoch. llmrun does not run this benchmark — see the source for methodology, or the about benchmarks for what it measures.