o-CoT versus MM CoT isolates reasoning supervision. Comparing Text CoT with MM CoT further measures the contribution of multimodal reasoning traces beyond text reasoning alone. All configurations initialize from the final Apertus 1.5 8B long-context pretraining checkpoint (Section 3.3) with a fresh optimizer state and are trained for two epochs. We use a sequence length of 8,192 with best-fit packing, a global batch size of 1,024 sequences (8.4M tokens per update), and a constant learning rate of 8×10−58\times 10^{-5} after 28 warmup updates. The multimodal configurations are trained with three seeds and the text-only configurations with one. We evaluate every configuration with thinking forced off or on, banning the opening token or prefilling it, since after SFT enabling thinking alone does not reliably make the model reason.
Table 11: Configuration of the SFT ablation. Conversations are reported per epoch and tokens over the full two-epoch run. CoT and No-CoT arms use the same conversations and differ only in whether reasoning traces are retained.
Arm
Training Data
Traces
Conversations
Tokens
Updates
Text No-CoT
Text
No
3.48M
4.4B
535
Text CoT
Text
Yes
3.48M
10.2B
1,211
MM No-CoT
Text + multimodal
No
7.40M
19.6B
2,352
MM CoT
Text + multimodal
Yes
7.40M
27.5B
3,290
No-CoTOffCoTOffCoTOn−4-4−2-200+2+2+4+4
0.00.0+0.9+0.9+3.1+3.1
Score change (pp)Q1 Does multimodal SFTimprove text performance?
Vision(14 tasks)Text(16 tasks)−4-4−2-200+2+2+4+4
+3.8+3.8+0.2+0.2
Q2 Do traces help visionwithout hurting text?
Vision(14 tasks)Text(16 tasks)−4-4−2-200+2+2+4+4
−2.2-2.20.00.0
Q3 Do traces help evenwith thinking off?
Mean change
Individual seed
Figure 12: SFT ablations of multimodal supervision and reasoning, one panel per question. Q1 compares text benchmark scores for MM No-CoT versus Text No-CoT and MM CoT versus Text CoT, evaluated under matched response modes. Q2 compares MM CoT with thinking on against MM No-CoT with thinking off. Q3 compares MM CoT against MM No-CoT, both with thinking off. Bars report mean score differences in percentage points; dots denote the three multimodal seeds. Comparisons use a single text-only reference seed in Q1 and paired seeds in Q2 and Q3. Scores are unweighted means over 16 text benchmarks, excluding MGSM (Table H.1 gives the reason), and 14 vision benchmarks. Without thinking, decoding is greedy with a 16,384-token budget; thinking is sampled at temperature 0.6 and top-p 0.95 with a 32,768-token budget.
Figure 12answers Q1 to Q3 with one panel each. For Q1, adding multimodal SFT data preserves text performance; when multimodal reasoning traces are retained, text performance even improves on average over the model trained only on text reasoning. For Q2, reasoning-trace supervision provides a clear benefit on multimodal tasks when reasoning is enabled at inference time, while its effect on aggregate text performance remains negligible. However, for Q3, the multimodal benefit turns into a small loss when reasoning is disabled: trace supervision lowers vision scores by 2.2 points on average, consistently across all three seeds, while text is unaffected. The averages hide large per-benchmark effects (Section H.1 in Appendix H): with thinking on, trace supervision adds seven to 18 points on mathematics but costs 12 to 14 on IFEval and Multi-IF, mostly because about a quarter of traces degenerate into repetition and never finish.
Takeaway.
Multimodal supervision can be integrated at scale during SFT without sacrificing text capabilities, and reasoning-trace supervision pays off primarily when the model is allowed to reason at inference time.
Q4.
Whether reasoning supervision during SFT provides a better starting point for subsequent RL remains unsettled. In text reasoning, prior work finds both that SFT can constrain later exploration (Kang et al., 2026) and that stronger reasoning SFT can improve the initialization for RL (Liu et al., 2026); off-policy reasoning traces can also be beneficial when combined