From 7c72202f1358be0b376f9ca40e8104a1871f8fc8 Mon Sep 17 00:00:00 2001
From: spiffytech <spiffy@spiffy.tech>
Date: Thu, 12 Mar 2026 10:13:22 -0400
Subject: [PATCH] Added Ollama Cloud benchmarks

---
 README.md | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/README.md b/README.md
index cdeb4ce..af9e320 100644
--- a/README.md
+++ b/README.md
@@ -43,6 +43,11 @@ add more provider results!
 |Parasail |GLM-4.7         |:x: 83%|
 |Parasail |Kimi K2 Thinking|:x: 75%|
 
+|Provider |Model           |Success Rate|
+|---------|----------------|------------|
+|Ollama Cloud |GLM-4.7         |:x: 88%|
+|Ollama Cloud |Minimax M2|:x: 62%|
+
 Note for attempting reproductions: generally all tests are reproducible with
 `--count 1` and `--count 1 --stream`, but for evaluating the
 response-in-reasoning eval, you generally will need a high count to reproduce