Mistral Large 4 High vs Muse Spark Open compared

If you only looked at the intelligence index, Mistral Large 4 (High) and Muse Spark Open (Xhigh) would be hard to tell apart. Cost is where they split the most, with Mistral Large 4 High working out at about 52% of Muse Spark Open's blended rate. Everything below is read from the benchmark, price and speed data in Franklin AI's catalogue; nothing here comes from a hands-on test.

Running costs

The list prices are $0.70 in and $2.10 out for Mistral Large 4 High, and $1.25 in and $4.25 out for Muse Spark Open, per million tokens. That makes Mistral Large 4 High's output 51% cheaper.

For a sample workload of 1 million input tokens and 200,000 output tokens, Mistral Large 4 High would cost $1.12 and Muse Spark Open $2.10, a difference of $0.98. For extracting fields from 20,000 pages of 1,500 tokens into 150-token records, Mistral Large 4 High would come in 46% lower: $27.30 for Mistral Large 4 High against $50.25 for Muse Spark Open.

Generation gap

Mistral Large 4 High arrived on October 29, 2026, 14 days after Muse Spark Open (October 15, 2026). They are effectively contemporaries.

Waiting time

Mistral Large 4 High generates about 139 tokens per second and Muse Spark Open about 207 tokens per second. That makes Muse Spark Open roughly 1.5 times as fast at writing. Before any text appears, Mistral Large 4 High takes 1.7 seconds and Muse Spark Open 0.94 seconds. Mistral Large 4 High waits 1.9 times as long before its first token.

Put together, a 400-token answer would take about 4.6 seconds from Mistral Large 4 High and 2.9 seconds from Muse Spark Open, counting the first-token wait.

Overall capability: 1.2 points apart

The catalogue puts Mistral Large 4 High at 26.1 and Muse Spark Open at 24.9 on its intelligence index. The lead is visible but narrow, so it should not decide the choice on its own. Put another way, Muse Spark Open would need 5% more on this index to draw level.

For context, that places Mistral Large 4 High 65th and Muse Spark Open 68th out of 109 scored models still on offer.

The catalogue does not yet split either model's score into coding and math indexes.

Value for money

Per point of intelligence index, Mistral Large 4 High costs $0.040 of blended price per million tokens and Muse Spark Open $0.080. Mistral Large 4 High scores higher and costs less per point, so on price per point there is nothing to trade off.