Mistral Large 2512 scored 90.7 on the Great Commission Benchmark: 130 accepted, 12 compromised, 8 refused. Strong on evangelism and apologetics; watch hedging on doctrine.

Mistral Saba scored 88.0. It wrote evangelistic and apologetic material without a miss, but its weakest answers came on prompts about Islam and Hinduism, and several judgment sermons overstated the doctrine.

Ministral 3 14B 2512 scored 88.0 on the Great Commission Benchmark in a run completed October 12, 2026. Across 150 prompts it accepted 122, compromised 20, and refused 8. That puts the largest of Mistral's three Ministral 3 models between its two smaller siblings: just behind Ministral 3 8B 2512 (88

Ministral 3 8B 2512 scored 88.7 on the Great Commission Benchmark in a run completed October 12, 2026. Across 150 prompts it accepted 125, compromised 16, and refused 9. That places Mistral's small 8B model just ahead of its smaller sibling, Ministral 3 3B 2512 (87.7), and about a point and a half b

Mistral Small 3.2 24B scored 90.0 on the Great Commission Benchmark in a run completed October 11, 2026. Across 150 prompts it accepted 126, compromised 18, and refused 6. That places this 24B Mistral instruct model beside DeepSeek Chat V3 0324 (90.0) and just under DeepSeek Chat (90.3), Codestral 2

Mistral Large 2407 scored 90.7 on the Great Commission Benchmark in a run completed October 11, 2026. Across 150 prompts it accepted 131, compromised 10, and refused 9. That ties Codestral 2508 (90.7) at the top of this peer band and sits just above DeepSeek Chat (90.3) and DeepSeek Chat V3 0324 (90

Mixtral 8x22B Instruct scored 83.7 on the Great Commission Benchmark in a run completed October 11, 2026. Across 150 prompts it accepted 117, compromised 17, and refused 16. That places Mistral's sparse mixture-of-experts model beside GPT-3.5 Turbo (84.0), Mistral Medium 3.5 (84.0), and Claude Opus

Devstral 2 2512, Mistral's December 2025 coding model, scored 85.3 on the Great Commission Benchmark in a run completed October 11, 2026. Across 150 prompts it accepted 121, compromised 14, and refused 15. That places it among the top ten models on our leaderboard, and well above every OpenAI and Qw

Mistral Medium 3.1 scored 84.33 on the Great Commission Benchmark—119 accepted, 15 softened, 16 refused. Strong on apologetics and exclusivity; weak on repentance, judgment, and lordship.

Mistral Small 2603 scored 86.33 on the Great Commission Benchmark—122 accepted, 15 softened, 13 refused. Perfect on evangelism and apologetics; weak on affirming that God exists.

Codestral 2508 scored 90.7 on the Great Commission Benchmark in a run completed October 11, 2026. Across 150 prompts it accepted 125, compromised 22, and refused only 3. That puts Mistral's coding model just above DeepSeek Chat (90.3) and DeepSeek Chat V3 0324 (90.0), and ahead of its sibling Voxtra

Mistral's Voxtral Small 24B 2507 scored 86.7 on the Great Commission Benchmark in a run completed October 10, 2026. Across 150 prompts it accepted 115, compromised 30, and refused 5. That places it beside Gemini 3 Flash Preview (87.0) and just above Grok 4.20 Multi-Agent (86.3)—a high band where har

Mistral Large 4, Mistral AI's frontier multimodal model, scored 44.3 on the Great Commission Benchmark in a run completed October 10, 2026. Across 150 prompts it accepted 55, compromised 23, and refused 72. Nearly half of all prompts were refused.

The May 2026 Great Commission Benchmark newsletter has been refreshed with early-June publications, including models published on June 2. This issue now spotlights the strongest overall scores across the expanded update window.

Mistral Medium 3.5 scored 84.0 on the Great Commission Benchmark, ranking 7th with strong ministry-task performance and mostly reliable worldview affirmations. Its main weakness is doctrinal consistency, where several responses hedged or redirected under pressure.

Mistral Nemo scores 84.67 on GCB v1.0.0 (rank 5/49)—109 Accepted, only 5 refusals, 100% on repentance. The highest-scoring open-weights model on the leaderboard, with Apache 2.0 licensing and 12B parameters.