Clinical Benchmarks
Menu

Llama 3.1 70B

Released 23 Jul 2024128K context70BopenAlso written as Llama-3.1-70B

7 results on 1 of 13 boards, 6 of them on secondary measures, latest measured Aug 2026. Compare with other models

Clinical Benchmarks Index22.7Rank 103 of 1491 of 10 boardsAverage × multiplier 55.7 × 0.408 = 22.7This site’s own calculation. Working How it is computed

Results

Each line sits on its own board's scale. Tall tick: the board leader.

Safety

  1. MedPIC
    zero-shot; independent questions; exact option-set match
    55.7
    Rank 15 of 28Leader Gemini-3.1-Pro 80.7
    Independent run
    Measured Aug 2026

Index working

The Clinical Benchmarks Index is this site's own calculation: a weighted average of the board scores times a multiplier for the boards behind it. How it is computed

  • MedPIC55.755.7×0.482, near its ceilingNear its ceiling: leader 80.7, weight 0.482zero-shot; independent questions; exact option-set match
One board, so its score
55.7
Multiplier for 1 of 10 boards
× 0.408
Index
55.7 × 0.408 = 22.7

Score: the result on the board’s own 0 to 100 scale. Dot: this model; tick: the board’s leader. Weight: how much the board counts in the weighted average; bold where the board is near its ceiling and counts for less. Each result links to its quote and page; the line under it is the setting it was measured with.

Secondary measures

Safety

  1. MedPIC, Risk activation accuracy
    zero-shot; independent questions; exact option-set match
    63.4
    Rank 8 of 28Leader MedGemma-27B-Text 76.1
    Independent run
    Measured Aug 2026
  2. MedPIC, Counterfactual accuracy (CF)
    zero-shot; independent questions; exact option-set match
    47.0
    Rank 15 of 28Leader Gemini-3.1-Pro 69.9
    Independent run
    Measured Aug 2026
  3. MedPIC, Guideline-following accuracy (GF)
    zero-shot; independent questions; exact option-set match
    61.3
    Rank 16 of 28Leader Gemini-3.1-Pro 87.7
    Independent run
    Measured Aug 2026
  4. MedPIC, Linked counterfactual pair accuracy
    zero-shot; independent questions; exact option-set match
    16.9
    Rank 16 of 28Leader Gemini-3.1-Pro 48.3
    Independent run
    Measured Aug 2026
  5. MedPIC, Risk deactivation accuracy
    zero-shot; independent questions; exact option-set match
    32.4
    Rank 16 of 28Leader Gemini-3.1-Pro 77.9
    Independent run
    Measured Aug 2026
  6. MedPIC, Published GF-minus-CF accuracy gap
    zero-shot; independent questions; exact option-set match
    14.3
    Descriptive measure, not ranked
    Independent run
    Measured Aug 2026

Sources

The quote, page and document for each of the 7 results
  1. 15MedPIC zero-shot 55.7
    Printed as 55.7Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set match
    Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row Llama-3.1-70B, column Overall; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | Pair
    Llama-3.1-70B | 55.7 | 61.3 | 47.0 | 14.3 | 63.4 | 32.4 | 16.9
    Every result from this document
  2. 16MedPIC, Guideline-following accuracy (GF) zero-shot 61.3
    Printed as 61.3Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set match
    Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row Llama-3.1-70B, column GF; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | Pair
    Llama-3.1-70B | 55.7 | 61.3 | 47.0 | 14.3 | 63.4 | 32.4 | 16.9
    Every result from this document
  3. 15MedPIC, Counterfactual accuracy (CF) zero-shot 47.0
    Printed as 47.0Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set match
    Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row Llama-3.1-70B, column CF; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | Pair
    Llama-3.1-70B | 55.7 | 61.3 | 47.0 | 14.3 | 63.4 | 32.4 | 16.9
    Every result from this document
  4. 16MedPIC, Linked counterfactual pair accuracy zero-shot 16.9
    Printed as 16.9Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set match
    Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row Llama-3.1-70B, column Pair; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | Pair
    Llama-3.1-70B | 55.7 | 61.3 | 47.0 | 14.3 | 63.4 | 32.4 | 16.9
    Every result from this document
  5. 8MedPIC, Risk activation accuracy zero-shot 63.4
    Printed as 63.4Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set match
    Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row Llama-3.1-70B, column Activation; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | Pair
    Llama-3.1-70B | 55.7 | 61.3 | 47.0 | 14.3 | 63.4 | 32.4 | 16.9
    Every result from this document
  6. 16MedPIC, Risk deactivation accuracy zero-shot 32.4
    Printed as 32.4Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set match
    Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row Llama-3.1-70B, column Deactivation; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | Pair
    Llama-3.1-70B | 55.7 | 61.3 | 47.0 | 14.3 | 63.4 | 32.4 | 16.9
    Every result from this document
  7. –MedPIC, Published GF-minus-CF accuracy gap zero-shot 14.3
    Printed as 14.3Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set match
    Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row Llama-3.1-70B, column Δ_GF−CF; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | Pair
    Llama-3.1-70B | 55.7 | 61.3 | 47.0 | 14.3 | 63.4 | 32.4 | 16.9
    Every result from this document

Other Meta models: Llama 3.1 8B, Llama 4 Maverick, Llama 4 Scout, Muse Spark, Muse Spark 1.1, Muse Spark 1.2